Joshua Lochner
commited on
Commit
·
26c7c20
1
Parent(s):
ce06bcf
Update whisper models
Browse filesThis view is limited to 50 files because it contains too many changes.
See raw diff
- quantized/openai/whisper-base.en/default/config.json +10 -1
- quantized/openai/whisper-base.en/default/generation_config.json +0 -112
- quantized/openai/whisper-base.en/default/merges.txt +1 -1
- quantized/openai/whisper-base.en/default/{decoder_model.onnx → model.onnx} +2 -2
- quantized/openai/whisper-base.en/default/tokenizer.json +216 -218
- quantized/openai/whisper-base.en/default/tokenizer_config.json +0 -1
- quantized/openai/whisper-base.en/default/vocab.json +0 -0
- quantized/openai/whisper-base.en/speech2seq-lm-with-past/config.json +10 -1
- quantized/openai/whisper-base.en/speech2seq-lm-with-past/decoder_model.onnx +2 -2
- quantized/openai/whisper-base.en/speech2seq-lm-with-past/decoder_model_merged.onnx +2 -2
- quantized/openai/whisper-base.en/speech2seq-lm-with-past/decoder_with_past_model.onnx +2 -2
- quantized/openai/whisper-base.en/speech2seq-lm-with-past/encoder_model.onnx +2 -2
- quantized/openai/whisper-base.en/speech2seq-lm-with-past/merges.txt +1 -1
- quantized/openai/whisper-base.en/speech2seq-lm-with-past/tokenizer.json +216 -218
- quantized/openai/whisper-base.en/speech2seq-lm-with-past/tokenizer_config.json +0 -1
- quantized/openai/whisper-base.en/speech2seq-lm-with-past/vocab.json +0 -0
- quantized/openai/whisper-base/default/config.json +10 -1
- quantized/openai/whisper-base/default/generation_config.json +0 -219
- quantized/openai/whisper-base/default/merges.txt +1 -1
- quantized/openai/{whisper-base.en/default/encoder_model.onnx → whisper-base/default/model.onnx} +2 -2
- quantized/openai/whisper-base/default/tokenizer.json +216 -218
- quantized/openai/whisper-base/default/tokenizer_config.json +0 -1
- quantized/openai/whisper-base/default/vocab.json +0 -0
- quantized/openai/whisper-base/speech2seq-lm-with-past/config.json +10 -1
- quantized/openai/whisper-base/speech2seq-lm-with-past/decoder_model.onnx +2 -2
- quantized/openai/whisper-base/speech2seq-lm-with-past/decoder_model_merged.onnx +2 -2
- quantized/openai/whisper-base/speech2seq-lm-with-past/decoder_with_past_model.onnx +2 -2
- quantized/openai/whisper-base/speech2seq-lm-with-past/encoder_model.onnx +2 -2
- quantized/openai/whisper-base/speech2seq-lm-with-past/merges.txt +1 -1
- quantized/openai/whisper-base/speech2seq-lm-with-past/tokenizer.json +216 -218
- quantized/openai/whisper-base/speech2seq-lm-with-past/tokenizer_config.json +0 -1
- quantized/openai/whisper-base/speech2seq-lm-with-past/vocab.json +0 -0
- quantized/openai/whisper-small.en/default/config.json +10 -1
- quantized/openai/whisper-small.en/default/decoder_model.onnx +0 -3
- quantized/openai/whisper-small.en/default/encoder_model.onnx +0 -3
- quantized/openai/whisper-small.en/default/generation_config.json +0 -111
- quantized/openai/whisper-small.en/default/merges.txt +1 -1
- quantized/openai/whisper-small.en/default/model.onnx +3 -0
- quantized/openai/whisper-small.en/default/tokenizer.json +216 -218
- quantized/openai/whisper-small.en/default/tokenizer_config.json +0 -1
- quantized/openai/whisper-small.en/default/vocab.json +0 -0
- quantized/openai/whisper-small.en/speech2seq-lm-with-past/config.json +10 -1
- quantized/openai/whisper-small.en/speech2seq-lm-with-past/decoder_model.onnx +2 -2
- quantized/openai/whisper-small.en/speech2seq-lm-with-past/decoder_model_merged.onnx +2 -2
- quantized/openai/whisper-small.en/speech2seq-lm-with-past/decoder_with_past_model.onnx +2 -2
- quantized/openai/whisper-small.en/speech2seq-lm-with-past/encoder_model.onnx +2 -2
- quantized/openai/whisper-small.en/speech2seq-lm-with-past/merges.txt +1 -1
- quantized/openai/whisper-small.en/speech2seq-lm-with-past/tokenizer.json +216 -218
- quantized/openai/whisper-small.en/speech2seq-lm-with-past/tokenizer_config.json +0 -1
- quantized/openai/whisper-small.en/speech2seq-lm-with-past/vocab.json +0 -0
quantized/openai/whisper-base.en/default/config.json
CHANGED
|
@@ -2,6 +2,7 @@
|
|
| 2 |
"_name_or_path": "openai/whisper-base.en",
|
| 3 |
"activation_dropout": 0.0,
|
| 4 |
"activation_function": "gelu",
|
|
|
|
| 5 |
"architectures": [
|
| 6 |
"WhisperForConditionalGeneration"
|
| 7 |
],
|
|
@@ -11,6 +12,7 @@
|
|
| 11 |
50256
|
| 12 |
],
|
| 13 |
"bos_token_id": 50257,
|
|
|
|
| 14 |
"d_model": 512,
|
| 15 |
"decoder_attention_heads": 8,
|
| 16 |
"decoder_ffn_dim": 2048,
|
|
@@ -31,6 +33,12 @@
|
|
| 31 |
],
|
| 32 |
"init_std": 0.02,
|
| 33 |
"is_encoder_decoder": true,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 34 |
"max_length": 448,
|
| 35 |
"max_source_positions": 1500,
|
| 36 |
"max_target_positions": 448,
|
|
@@ -129,7 +137,8 @@
|
|
| 129 |
50360,
|
| 130 |
50361
|
| 131 |
],
|
| 132 |
-
"transformers_version": "4.
|
| 133 |
"use_cache": true,
|
|
|
|
| 134 |
"vocab_size": 51864
|
| 135 |
}
|
|
|
|
| 2 |
"_name_or_path": "openai/whisper-base.en",
|
| 3 |
"activation_dropout": 0.0,
|
| 4 |
"activation_function": "gelu",
|
| 5 |
+
"apply_spec_augment": false,
|
| 6 |
"architectures": [
|
| 7 |
"WhisperForConditionalGeneration"
|
| 8 |
],
|
|
|
|
| 12 |
50256
|
| 13 |
],
|
| 14 |
"bos_token_id": 50257,
|
| 15 |
+
"classifier_proj_size": 256,
|
| 16 |
"d_model": 512,
|
| 17 |
"decoder_attention_heads": 8,
|
| 18 |
"decoder_ffn_dim": 2048,
|
|
|
|
| 33 |
],
|
| 34 |
"init_std": 0.02,
|
| 35 |
"is_encoder_decoder": true,
|
| 36 |
+
"mask_feature_length": 10,
|
| 37 |
+
"mask_feature_min_masks": 0,
|
| 38 |
+
"mask_feature_prob": 0.0,
|
| 39 |
+
"mask_time_length": 10,
|
| 40 |
+
"mask_time_min_masks": 2,
|
| 41 |
+
"mask_time_prob": 0.05,
|
| 42 |
"max_length": 448,
|
| 43 |
"max_source_positions": 1500,
|
| 44 |
"max_target_positions": 448,
|
|
|
|
| 137 |
50360,
|
| 138 |
50361
|
| 139 |
],
|
| 140 |
+
"transformers_version": "4.27.2",
|
| 141 |
"use_cache": true,
|
| 142 |
+
"use_weighted_layer_sum": false,
|
| 143 |
"vocab_size": 51864
|
| 144 |
}
|
quantized/openai/whisper-base.en/default/generation_config.json
DELETED
|
@@ -1,112 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"begin_suppress_tokens": [
|
| 3 |
-
220,
|
| 4 |
-
50256
|
| 5 |
-
],
|
| 6 |
-
"bos_token_id": 50257,
|
| 7 |
-
"decoder_start_token_id": 50257,
|
| 8 |
-
"eos_token_id": 50256,
|
| 9 |
-
"forced_decoder_ids": [
|
| 10 |
-
[
|
| 11 |
-
1,
|
| 12 |
-
50362
|
| 13 |
-
]
|
| 14 |
-
],
|
| 15 |
-
"is_multilingual": false,
|
| 16 |
-
"max_initial_timestamp_index": 1,
|
| 17 |
-
"max_length": 448,
|
| 18 |
-
"no_timestamps_token_id": 50362,
|
| 19 |
-
"pad_token_id": 50256,
|
| 20 |
-
"return_timestamps": false,
|
| 21 |
-
"suppress_tokens": [
|
| 22 |
-
1,
|
| 23 |
-
2,
|
| 24 |
-
7,
|
| 25 |
-
8,
|
| 26 |
-
9,
|
| 27 |
-
10,
|
| 28 |
-
14,
|
| 29 |
-
25,
|
| 30 |
-
26,
|
| 31 |
-
27,
|
| 32 |
-
28,
|
| 33 |
-
29,
|
| 34 |
-
31,
|
| 35 |
-
58,
|
| 36 |
-
59,
|
| 37 |
-
60,
|
| 38 |
-
61,
|
| 39 |
-
62,
|
| 40 |
-
63,
|
| 41 |
-
90,
|
| 42 |
-
91,
|
| 43 |
-
92,
|
| 44 |
-
93,
|
| 45 |
-
357,
|
| 46 |
-
366,
|
| 47 |
-
438,
|
| 48 |
-
532,
|
| 49 |
-
685,
|
| 50 |
-
705,
|
| 51 |
-
796,
|
| 52 |
-
930,
|
| 53 |
-
1058,
|
| 54 |
-
1220,
|
| 55 |
-
1267,
|
| 56 |
-
1279,
|
| 57 |
-
1303,
|
| 58 |
-
1343,
|
| 59 |
-
1377,
|
| 60 |
-
1391,
|
| 61 |
-
1635,
|
| 62 |
-
1782,
|
| 63 |
-
1875,
|
| 64 |
-
2162,
|
| 65 |
-
2361,
|
| 66 |
-
2488,
|
| 67 |
-
3467,
|
| 68 |
-
4008,
|
| 69 |
-
4211,
|
| 70 |
-
4600,
|
| 71 |
-
4808,
|
| 72 |
-
5299,
|
| 73 |
-
5855,
|
| 74 |
-
6329,
|
| 75 |
-
7203,
|
| 76 |
-
9609,
|
| 77 |
-
9959,
|
| 78 |
-
10563,
|
| 79 |
-
10786,
|
| 80 |
-
11420,
|
| 81 |
-
11709,
|
| 82 |
-
11907,
|
| 83 |
-
13163,
|
| 84 |
-
13697,
|
| 85 |
-
13700,
|
| 86 |
-
14808,
|
| 87 |
-
15306,
|
| 88 |
-
16410,
|
| 89 |
-
16791,
|
| 90 |
-
17992,
|
| 91 |
-
19203,
|
| 92 |
-
19510,
|
| 93 |
-
20724,
|
| 94 |
-
22305,
|
| 95 |
-
22935,
|
| 96 |
-
27007,
|
| 97 |
-
30109,
|
| 98 |
-
30420,
|
| 99 |
-
33409,
|
| 100 |
-
34949,
|
| 101 |
-
40283,
|
| 102 |
-
40493,
|
| 103 |
-
40549,
|
| 104 |
-
47282,
|
| 105 |
-
49146,
|
| 106 |
-
50257,
|
| 107 |
-
50359,
|
| 108 |
-
50360,
|
| 109 |
-
50361
|
| 110 |
-
],
|
| 111 |
-
"transformers_version": "4.27.0.dev0"
|
| 112 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
quantized/openai/whisper-base.en/default/merges.txt
CHANGED
|
@@ -1,4 +1,4 @@
|
|
| 1 |
-
#version: 0.2
|
| 2 |
Ġ t
|
| 3 |
Ġ a
|
| 4 |
h e
|
|
|
|
| 1 |
+
#version: 0.2 - Trained by `huggingface/tokenizers`
|
| 2 |
Ġ t
|
| 3 |
Ġ a
|
| 4 |
h e
|
quantized/openai/whisper-base.en/default/{decoder_model.onnx → model.onnx}
RENAMED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:72b7e5633c375bd177e5c7370be5606f093578b30bcb9e584c58a73e92f41701
|
| 3 |
+
size 76778687
|
quantized/openai/whisper-base.en/default/tokenizer.json
CHANGED
|
@@ -5,974 +5,973 @@
|
|
| 5 |
"added_tokens": [
|
| 6 |
{
|
| 7 |
"id": 50256,
|
|
|
|
| 8 |
"content": "<|endoftext|>",
|
| 9 |
"single_word": false,
|
| 10 |
"lstrip": false,
|
| 11 |
"rstrip": false,
|
| 12 |
-
"normalized": false
|
| 13 |
-
"special": true
|
| 14 |
},
|
| 15 |
{
|
| 16 |
"id": 50257,
|
|
|
|
| 17 |
"content": "<|startoftranscript|>",
|
| 18 |
"single_word": false,
|
| 19 |
"lstrip": false,
|
| 20 |
"rstrip": false,
|
| 21 |
-
"normalized": false
|
| 22 |
-
"special": true
|
| 23 |
},
|
| 24 |
{
|
| 25 |
"id": 50258,
|
|
|
|
| 26 |
"content": "<|en|>",
|
| 27 |
"single_word": false,
|
| 28 |
"lstrip": false,
|
| 29 |
"rstrip": false,
|
| 30 |
-
"normalized": false
|
| 31 |
-
"special": true
|
| 32 |
},
|
| 33 |
{
|
| 34 |
"id": 50259,
|
|
|
|
| 35 |
"content": "<|zh|>",
|
| 36 |
"single_word": false,
|
| 37 |
"lstrip": false,
|
| 38 |
"rstrip": false,
|
| 39 |
-
"normalized": false
|
| 40 |
-
"special": true
|
| 41 |
},
|
| 42 |
{
|
| 43 |
"id": 50260,
|
|
|
|
| 44 |
"content": "<|de|>",
|
| 45 |
"single_word": false,
|
| 46 |
"lstrip": false,
|
| 47 |
"rstrip": false,
|
| 48 |
-
"normalized": false
|
| 49 |
-
"special": true
|
| 50 |
},
|
| 51 |
{
|
| 52 |
"id": 50261,
|
|
|
|
| 53 |
"content": "<|es|>",
|
| 54 |
"single_word": false,
|
| 55 |
"lstrip": false,
|
| 56 |
"rstrip": false,
|
| 57 |
-
"normalized": false
|
| 58 |
-
"special": true
|
| 59 |
},
|
| 60 |
{
|
| 61 |
"id": 50262,
|
|
|
|
| 62 |
"content": "<|ru|>",
|
| 63 |
"single_word": false,
|
| 64 |
"lstrip": false,
|
| 65 |
"rstrip": false,
|
| 66 |
-
"normalized": false
|
| 67 |
-
"special": true
|
| 68 |
},
|
| 69 |
{
|
| 70 |
"id": 50263,
|
|
|
|
| 71 |
"content": "<|ko|>",
|
| 72 |
"single_word": false,
|
| 73 |
"lstrip": false,
|
| 74 |
"rstrip": false,
|
| 75 |
-
"normalized": false
|
| 76 |
-
"special": true
|
| 77 |
},
|
| 78 |
{
|
| 79 |
"id": 50264,
|
|
|
|
| 80 |
"content": "<|fr|>",
|
| 81 |
"single_word": false,
|
| 82 |
"lstrip": false,
|
| 83 |
"rstrip": false,
|
| 84 |
-
"normalized": false
|
| 85 |
-
"special": true
|
| 86 |
},
|
| 87 |
{
|
| 88 |
"id": 50265,
|
|
|
|
| 89 |
"content": "<|ja|>",
|
| 90 |
"single_word": false,
|
| 91 |
"lstrip": false,
|
| 92 |
"rstrip": false,
|
| 93 |
-
"normalized": false
|
| 94 |
-
"special": true
|
| 95 |
},
|
| 96 |
{
|
| 97 |
"id": 50266,
|
|
|
|
| 98 |
"content": "<|pt|>",
|
| 99 |
"single_word": false,
|
| 100 |
"lstrip": false,
|
| 101 |
"rstrip": false,
|
| 102 |
-
"normalized": false
|
| 103 |
-
"special": true
|
| 104 |
},
|
| 105 |
{
|
| 106 |
"id": 50267,
|
|
|
|
| 107 |
"content": "<|tr|>",
|
| 108 |
"single_word": false,
|
| 109 |
"lstrip": false,
|
| 110 |
"rstrip": false,
|
| 111 |
-
"normalized": false
|
| 112 |
-
"special": true
|
| 113 |
},
|
| 114 |
{
|
| 115 |
"id": 50268,
|
|
|
|
| 116 |
"content": "<|pl|>",
|
| 117 |
"single_word": false,
|
| 118 |
"lstrip": false,
|
| 119 |
"rstrip": false,
|
| 120 |
-
"normalized": false
|
| 121 |
-
"special": true
|
| 122 |
},
|
| 123 |
{
|
| 124 |
"id": 50269,
|
|
|
|
| 125 |
"content": "<|ca|>",
|
| 126 |
"single_word": false,
|
| 127 |
"lstrip": false,
|
| 128 |
"rstrip": false,
|
| 129 |
-
"normalized": false
|
| 130 |
-
"special": true
|
| 131 |
},
|
| 132 |
{
|
| 133 |
"id": 50270,
|
|
|
|
| 134 |
"content": "<|nl|>",
|
| 135 |
"single_word": false,
|
| 136 |
"lstrip": false,
|
| 137 |
"rstrip": false,
|
| 138 |
-
"normalized": false
|
| 139 |
-
"special": true
|
| 140 |
},
|
| 141 |
{
|
| 142 |
"id": 50271,
|
|
|
|
| 143 |
"content": "<|ar|>",
|
| 144 |
"single_word": false,
|
| 145 |
"lstrip": false,
|
| 146 |
"rstrip": false,
|
| 147 |
-
"normalized": false
|
| 148 |
-
"special": true
|
| 149 |
},
|
| 150 |
{
|
| 151 |
"id": 50272,
|
|
|
|
| 152 |
"content": "<|sv|>",
|
| 153 |
"single_word": false,
|
| 154 |
"lstrip": false,
|
| 155 |
"rstrip": false,
|
| 156 |
-
"normalized": false
|
| 157 |
-
"special": true
|
| 158 |
},
|
| 159 |
{
|
| 160 |
"id": 50273,
|
|
|
|
| 161 |
"content": "<|it|>",
|
| 162 |
"single_word": false,
|
| 163 |
"lstrip": false,
|
| 164 |
"rstrip": false,
|
| 165 |
-
"normalized": false
|
| 166 |
-
"special": true
|
| 167 |
},
|
| 168 |
{
|
| 169 |
"id": 50274,
|
|
|
|
| 170 |
"content": "<|id|>",
|
| 171 |
"single_word": false,
|
| 172 |
"lstrip": false,
|
| 173 |
"rstrip": false,
|
| 174 |
-
"normalized": false
|
| 175 |
-
"special": true
|
| 176 |
},
|
| 177 |
{
|
| 178 |
"id": 50275,
|
|
|
|
| 179 |
"content": "<|hi|>",
|
| 180 |
"single_word": false,
|
| 181 |
"lstrip": false,
|
| 182 |
"rstrip": false,
|
| 183 |
-
"normalized": false
|
| 184 |
-
"special": true
|
| 185 |
},
|
| 186 |
{
|
| 187 |
"id": 50276,
|
|
|
|
| 188 |
"content": "<|fi|>",
|
| 189 |
"single_word": false,
|
| 190 |
"lstrip": false,
|
| 191 |
"rstrip": false,
|
| 192 |
-
"normalized": false
|
| 193 |
-
"special": true
|
| 194 |
},
|
| 195 |
{
|
| 196 |
"id": 50277,
|
|
|
|
| 197 |
"content": "<|vi|>",
|
| 198 |
"single_word": false,
|
| 199 |
"lstrip": false,
|
| 200 |
"rstrip": false,
|
| 201 |
-
"normalized": false
|
| 202 |
-
"special": true
|
| 203 |
},
|
| 204 |
{
|
| 205 |
"id": 50278,
|
|
|
|
| 206 |
"content": "<|iw|>",
|
| 207 |
"single_word": false,
|
| 208 |
"lstrip": false,
|
| 209 |
"rstrip": false,
|
| 210 |
-
"normalized": false
|
| 211 |
-
"special": true
|
| 212 |
},
|
| 213 |
{
|
| 214 |
"id": 50279,
|
|
|
|
| 215 |
"content": "<|uk|>",
|
| 216 |
"single_word": false,
|
| 217 |
"lstrip": false,
|
| 218 |
"rstrip": false,
|
| 219 |
-
"normalized": false
|
| 220 |
-
"special": true
|
| 221 |
},
|
| 222 |
{
|
| 223 |
"id": 50280,
|
|
|
|
| 224 |
"content": "<|el|>",
|
| 225 |
"single_word": false,
|
| 226 |
"lstrip": false,
|
| 227 |
"rstrip": false,
|
| 228 |
-
"normalized": false
|
| 229 |
-
"special": true
|
| 230 |
},
|
| 231 |
{
|
| 232 |
"id": 50281,
|
|
|
|
| 233 |
"content": "<|ms|>",
|
| 234 |
"single_word": false,
|
| 235 |
"lstrip": false,
|
| 236 |
"rstrip": false,
|
| 237 |
-
"normalized": false
|
| 238 |
-
"special": true
|
| 239 |
},
|
| 240 |
{
|
| 241 |
"id": 50282,
|
|
|
|
| 242 |
"content": "<|cs|>",
|
| 243 |
"single_word": false,
|
| 244 |
"lstrip": false,
|
| 245 |
"rstrip": false,
|
| 246 |
-
"normalized": false
|
| 247 |
-
"special": true
|
| 248 |
},
|
| 249 |
{
|
| 250 |
"id": 50283,
|
|
|
|
| 251 |
"content": "<|ro|>",
|
| 252 |
"single_word": false,
|
| 253 |
"lstrip": false,
|
| 254 |
"rstrip": false,
|
| 255 |
-
"normalized": false
|
| 256 |
-
"special": true
|
| 257 |
},
|
| 258 |
{
|
| 259 |
"id": 50284,
|
|
|
|
| 260 |
"content": "<|da|>",
|
| 261 |
"single_word": false,
|
| 262 |
"lstrip": false,
|
| 263 |
"rstrip": false,
|
| 264 |
-
"normalized": false
|
| 265 |
-
"special": true
|
| 266 |
},
|
| 267 |
{
|
| 268 |
"id": 50285,
|
|
|
|
| 269 |
"content": "<|hu|>",
|
| 270 |
"single_word": false,
|
| 271 |
"lstrip": false,
|
| 272 |
"rstrip": false,
|
| 273 |
-
"normalized": false
|
| 274 |
-
"special": true
|
| 275 |
},
|
| 276 |
{
|
| 277 |
"id": 50286,
|
|
|
|
| 278 |
"content": "<|ta|>",
|
| 279 |
"single_word": false,
|
| 280 |
"lstrip": false,
|
| 281 |
"rstrip": false,
|
| 282 |
-
"normalized": false
|
| 283 |
-
"special": true
|
| 284 |
},
|
| 285 |
{
|
| 286 |
"id": 50287,
|
|
|
|
| 287 |
"content": "<|no|>",
|
| 288 |
"single_word": false,
|
| 289 |
"lstrip": false,
|
| 290 |
"rstrip": false,
|
| 291 |
-
"normalized": false
|
| 292 |
-
"special": true
|
| 293 |
},
|
| 294 |
{
|
| 295 |
"id": 50288,
|
|
|
|
| 296 |
"content": "<|th|>",
|
| 297 |
"single_word": false,
|
| 298 |
"lstrip": false,
|
| 299 |
"rstrip": false,
|
| 300 |
-
"normalized": false
|
| 301 |
-
"special": true
|
| 302 |
},
|
| 303 |
{
|
| 304 |
"id": 50289,
|
|
|
|
| 305 |
"content": "<|ur|>",
|
| 306 |
"single_word": false,
|
| 307 |
"lstrip": false,
|
| 308 |
"rstrip": false,
|
| 309 |
-
"normalized": false
|
| 310 |
-
"special": true
|
| 311 |
},
|
| 312 |
{
|
| 313 |
"id": 50290,
|
|
|
|
| 314 |
"content": "<|hr|>",
|
| 315 |
"single_word": false,
|
| 316 |
"lstrip": false,
|
| 317 |
"rstrip": false,
|
| 318 |
-
"normalized": false
|
| 319 |
-
"special": true
|
| 320 |
},
|
| 321 |
{
|
| 322 |
"id": 50291,
|
|
|
|
| 323 |
"content": "<|bg|>",
|
| 324 |
"single_word": false,
|
| 325 |
"lstrip": false,
|
| 326 |
"rstrip": false,
|
| 327 |
-
"normalized": false
|
| 328 |
-
"special": true
|
| 329 |
},
|
| 330 |
{
|
| 331 |
"id": 50292,
|
|
|
|
| 332 |
"content": "<|lt|>",
|
| 333 |
"single_word": false,
|
| 334 |
"lstrip": false,
|
| 335 |
"rstrip": false,
|
| 336 |
-
"normalized": false
|
| 337 |
-
"special": true
|
| 338 |
},
|
| 339 |
{
|
| 340 |
"id": 50293,
|
|
|
|
| 341 |
"content": "<|la|>",
|
| 342 |
"single_word": false,
|
| 343 |
"lstrip": false,
|
| 344 |
"rstrip": false,
|
| 345 |
-
"normalized": false
|
| 346 |
-
"special": true
|
| 347 |
},
|
| 348 |
{
|
| 349 |
"id": 50294,
|
|
|
|
| 350 |
"content": "<|mi|>",
|
| 351 |
"single_word": false,
|
| 352 |
"lstrip": false,
|
| 353 |
"rstrip": false,
|
| 354 |
-
"normalized": false
|
| 355 |
-
"special": true
|
| 356 |
},
|
| 357 |
{
|
| 358 |
"id": 50295,
|
|
|
|
| 359 |
"content": "<|ml|>",
|
| 360 |
"single_word": false,
|
| 361 |
"lstrip": false,
|
| 362 |
"rstrip": false,
|
| 363 |
-
"normalized": false
|
| 364 |
-
"special": true
|
| 365 |
},
|
| 366 |
{
|
| 367 |
"id": 50296,
|
|
|
|
| 368 |
"content": "<|cy|>",
|
| 369 |
"single_word": false,
|
| 370 |
"lstrip": false,
|
| 371 |
"rstrip": false,
|
| 372 |
-
"normalized": false
|
| 373 |
-
"special": true
|
| 374 |
},
|
| 375 |
{
|
| 376 |
"id": 50297,
|
|
|
|
| 377 |
"content": "<|sk|>",
|
| 378 |
"single_word": false,
|
| 379 |
"lstrip": false,
|
| 380 |
"rstrip": false,
|
| 381 |
-
"normalized": false
|
| 382 |
-
"special": true
|
| 383 |
},
|
| 384 |
{
|
| 385 |
"id": 50298,
|
|
|
|
| 386 |
"content": "<|te|>",
|
| 387 |
"single_word": false,
|
| 388 |
"lstrip": false,
|
| 389 |
"rstrip": false,
|
| 390 |
-
"normalized": false
|
| 391 |
-
"special": true
|
| 392 |
},
|
| 393 |
{
|
| 394 |
"id": 50299,
|
|
|
|
| 395 |
"content": "<|fa|>",
|
| 396 |
"single_word": false,
|
| 397 |
"lstrip": false,
|
| 398 |
"rstrip": false,
|
| 399 |
-
"normalized": false
|
| 400 |
-
"special": true
|
| 401 |
},
|
| 402 |
{
|
| 403 |
"id": 50300,
|
|
|
|
| 404 |
"content": "<|lv|>",
|
| 405 |
"single_word": false,
|
| 406 |
"lstrip": false,
|
| 407 |
"rstrip": false,
|
| 408 |
-
"normalized": false
|
| 409 |
-
"special": true
|
| 410 |
},
|
| 411 |
{
|
| 412 |
"id": 50301,
|
|
|
|
| 413 |
"content": "<|bn|>",
|
| 414 |
"single_word": false,
|
| 415 |
"lstrip": false,
|
| 416 |
"rstrip": false,
|
| 417 |
-
"normalized": false
|
| 418 |
-
"special": true
|
| 419 |
},
|
| 420 |
{
|
| 421 |
"id": 50302,
|
|
|
|
| 422 |
"content": "<|sr|>",
|
| 423 |
"single_word": false,
|
| 424 |
"lstrip": false,
|
| 425 |
"rstrip": false,
|
| 426 |
-
"normalized": false
|
| 427 |
-
"special": true
|
| 428 |
},
|
| 429 |
{
|
| 430 |
"id": 50303,
|
|
|
|
| 431 |
"content": "<|az|>",
|
| 432 |
"single_word": false,
|
| 433 |
"lstrip": false,
|
| 434 |
"rstrip": false,
|
| 435 |
-
"normalized": false
|
| 436 |
-
"special": true
|
| 437 |
},
|
| 438 |
{
|
| 439 |
"id": 50304,
|
|
|
|
| 440 |
"content": "<|sl|>",
|
| 441 |
"single_word": false,
|
| 442 |
"lstrip": false,
|
| 443 |
"rstrip": false,
|
| 444 |
-
"normalized": false
|
| 445 |
-
"special": true
|
| 446 |
},
|
| 447 |
{
|
| 448 |
"id": 50305,
|
|
|
|
| 449 |
"content": "<|kn|>",
|
| 450 |
"single_word": false,
|
| 451 |
"lstrip": false,
|
| 452 |
"rstrip": false,
|
| 453 |
-
"normalized": false
|
| 454 |
-
"special": true
|
| 455 |
},
|
| 456 |
{
|
| 457 |
"id": 50306,
|
|
|
|
| 458 |
"content": "<|et|>",
|
| 459 |
"single_word": false,
|
| 460 |
"lstrip": false,
|
| 461 |
"rstrip": false,
|
| 462 |
-
"normalized": false
|
| 463 |
-
"special": true
|
| 464 |
},
|
| 465 |
{
|
| 466 |
"id": 50307,
|
|
|
|
| 467 |
"content": "<|mk|>",
|
| 468 |
"single_word": false,
|
| 469 |
"lstrip": false,
|
| 470 |
"rstrip": false,
|
| 471 |
-
"normalized": false
|
| 472 |
-
"special": true
|
| 473 |
},
|
| 474 |
{
|
| 475 |
"id": 50308,
|
|
|
|
| 476 |
"content": "<|br|>",
|
| 477 |
"single_word": false,
|
| 478 |
"lstrip": false,
|
| 479 |
"rstrip": false,
|
| 480 |
-
"normalized": false
|
| 481 |
-
"special": true
|
| 482 |
},
|
| 483 |
{
|
| 484 |
"id": 50309,
|
|
|
|
| 485 |
"content": "<|eu|>",
|
| 486 |
"single_word": false,
|
| 487 |
"lstrip": false,
|
| 488 |
"rstrip": false,
|
| 489 |
-
"normalized": false
|
| 490 |
-
"special": true
|
| 491 |
},
|
| 492 |
{
|
| 493 |
"id": 50310,
|
|
|
|
| 494 |
"content": "<|is|>",
|
| 495 |
"single_word": false,
|
| 496 |
"lstrip": false,
|
| 497 |
"rstrip": false,
|
| 498 |
-
"normalized": false
|
| 499 |
-
"special": true
|
| 500 |
},
|
| 501 |
{
|
| 502 |
"id": 50311,
|
|
|
|
| 503 |
"content": "<|hy|>",
|
| 504 |
"single_word": false,
|
| 505 |
"lstrip": false,
|
| 506 |
"rstrip": false,
|
| 507 |
-
"normalized": false
|
| 508 |
-
"special": true
|
| 509 |
},
|
| 510 |
{
|
| 511 |
"id": 50312,
|
|
|
|
| 512 |
"content": "<|ne|>",
|
| 513 |
"single_word": false,
|
| 514 |
"lstrip": false,
|
| 515 |
"rstrip": false,
|
| 516 |
-
"normalized": false
|
| 517 |
-
"special": true
|
| 518 |
},
|
| 519 |
{
|
| 520 |
"id": 50313,
|
|
|
|
| 521 |
"content": "<|mn|>",
|
| 522 |
"single_word": false,
|
| 523 |
"lstrip": false,
|
| 524 |
"rstrip": false,
|
| 525 |
-
"normalized": false
|
| 526 |
-
"special": true
|
| 527 |
},
|
| 528 |
{
|
| 529 |
"id": 50314,
|
|
|
|
| 530 |
"content": "<|bs|>",
|
| 531 |
"single_word": false,
|
| 532 |
"lstrip": false,
|
| 533 |
"rstrip": false,
|
| 534 |
-
"normalized": false
|
| 535 |
-
"special": true
|
| 536 |
},
|
| 537 |
{
|
| 538 |
"id": 50315,
|
|
|
|
| 539 |
"content": "<|kk|>",
|
| 540 |
"single_word": false,
|
| 541 |
"lstrip": false,
|
| 542 |
"rstrip": false,
|
| 543 |
-
"normalized": false
|
| 544 |
-
"special": true
|
| 545 |
},
|
| 546 |
{
|
| 547 |
"id": 50316,
|
|
|
|
| 548 |
"content": "<|sq|>",
|
| 549 |
"single_word": false,
|
| 550 |
"lstrip": false,
|
| 551 |
"rstrip": false,
|
| 552 |
-
"normalized": false
|
| 553 |
-
"special": true
|
| 554 |
},
|
| 555 |
{
|
| 556 |
"id": 50317,
|
|
|
|
| 557 |
"content": "<|sw|>",
|
| 558 |
"single_word": false,
|
| 559 |
"lstrip": false,
|
| 560 |
"rstrip": false,
|
| 561 |
-
"normalized": false
|
| 562 |
-
"special": true
|
| 563 |
},
|
| 564 |
{
|
| 565 |
"id": 50318,
|
|
|
|
| 566 |
"content": "<|gl|>",
|
| 567 |
"single_word": false,
|
| 568 |
"lstrip": false,
|
| 569 |
"rstrip": false,
|
| 570 |
-
"normalized": false
|
| 571 |
-
"special": true
|
| 572 |
},
|
| 573 |
{
|
| 574 |
"id": 50319,
|
|
|
|
| 575 |
"content": "<|mr|>",
|
| 576 |
"single_word": false,
|
| 577 |
"lstrip": false,
|
| 578 |
"rstrip": false,
|
| 579 |
-
"normalized": false
|
| 580 |
-
"special": true
|
| 581 |
},
|
| 582 |
{
|
| 583 |
"id": 50320,
|
|
|
|
| 584 |
"content": "<|pa|>",
|
| 585 |
"single_word": false,
|
| 586 |
"lstrip": false,
|
| 587 |
"rstrip": false,
|
| 588 |
-
"normalized": false
|
| 589 |
-
"special": true
|
| 590 |
},
|
| 591 |
{
|
| 592 |
"id": 50321,
|
|
|
|
| 593 |
"content": "<|si|>",
|
| 594 |
"single_word": false,
|
| 595 |
"lstrip": false,
|
| 596 |
"rstrip": false,
|
| 597 |
-
"normalized": false
|
| 598 |
-
"special": true
|
| 599 |
},
|
| 600 |
{
|
| 601 |
"id": 50322,
|
|
|
|
| 602 |
"content": "<|km|>",
|
| 603 |
"single_word": false,
|
| 604 |
"lstrip": false,
|
| 605 |
"rstrip": false,
|
| 606 |
-
"normalized": false
|
| 607 |
-
"special": true
|
| 608 |
},
|
| 609 |
{
|
| 610 |
"id": 50323,
|
|
|
|
| 611 |
"content": "<|sn|>",
|
| 612 |
"single_word": false,
|
| 613 |
"lstrip": false,
|
| 614 |
"rstrip": false,
|
| 615 |
-
"normalized": false
|
| 616 |
-
"special": true
|
| 617 |
},
|
| 618 |
{
|
| 619 |
"id": 50324,
|
|
|
|
| 620 |
"content": "<|yo|>",
|
| 621 |
"single_word": false,
|
| 622 |
"lstrip": false,
|
| 623 |
"rstrip": false,
|
| 624 |
-
"normalized": false
|
| 625 |
-
"special": true
|
| 626 |
},
|
| 627 |
{
|
| 628 |
"id": 50325,
|
|
|
|
| 629 |
"content": "<|so|>",
|
| 630 |
"single_word": false,
|
| 631 |
"lstrip": false,
|
| 632 |
"rstrip": false,
|
| 633 |
-
"normalized": false
|
| 634 |
-
"special": true
|
| 635 |
},
|
| 636 |
{
|
| 637 |
"id": 50326,
|
|
|
|
| 638 |
"content": "<|af|>",
|
| 639 |
"single_word": false,
|
| 640 |
"lstrip": false,
|
| 641 |
"rstrip": false,
|
| 642 |
-
"normalized": false
|
| 643 |
-
"special": true
|
| 644 |
},
|
| 645 |
{
|
| 646 |
"id": 50327,
|
|
|
|
| 647 |
"content": "<|oc|>",
|
| 648 |
"single_word": false,
|
| 649 |
"lstrip": false,
|
| 650 |
"rstrip": false,
|
| 651 |
-
"normalized": false
|
| 652 |
-
"special": true
|
| 653 |
},
|
| 654 |
{
|
| 655 |
"id": 50328,
|
|
|
|
| 656 |
"content": "<|ka|>",
|
| 657 |
"single_word": false,
|
| 658 |
"lstrip": false,
|
| 659 |
"rstrip": false,
|
| 660 |
-
"normalized": false
|
| 661 |
-
"special": true
|
| 662 |
},
|
| 663 |
{
|
| 664 |
"id": 50329,
|
|
|
|
| 665 |
"content": "<|be|>",
|
| 666 |
"single_word": false,
|
| 667 |
"lstrip": false,
|
| 668 |
"rstrip": false,
|
| 669 |
-
"normalized": false
|
| 670 |
-
"special": true
|
| 671 |
},
|
| 672 |
{
|
| 673 |
"id": 50330,
|
|
|
|
| 674 |
"content": "<|tg|>",
|
| 675 |
"single_word": false,
|
| 676 |
"lstrip": false,
|
| 677 |
"rstrip": false,
|
| 678 |
-
"normalized": false
|
| 679 |
-
"special": true
|
| 680 |
},
|
| 681 |
{
|
| 682 |
"id": 50331,
|
|
|
|
| 683 |
"content": "<|sd|>",
|
| 684 |
"single_word": false,
|
| 685 |
"lstrip": false,
|
| 686 |
"rstrip": false,
|
| 687 |
-
"normalized": false
|
| 688 |
-
"special": true
|
| 689 |
},
|
| 690 |
{
|
| 691 |
"id": 50332,
|
|
|
|
| 692 |
"content": "<|gu|>",
|
| 693 |
"single_word": false,
|
| 694 |
"lstrip": false,
|
| 695 |
"rstrip": false,
|
| 696 |
-
"normalized": false
|
| 697 |
-
"special": true
|
| 698 |
},
|
| 699 |
{
|
| 700 |
"id": 50333,
|
|
|
|
| 701 |
"content": "<|am|>",
|
| 702 |
"single_word": false,
|
| 703 |
"lstrip": false,
|
| 704 |
"rstrip": false,
|
| 705 |
-
"normalized": false
|
| 706 |
-
"special": true
|
| 707 |
},
|
| 708 |
{
|
| 709 |
"id": 50334,
|
|
|
|
| 710 |
"content": "<|yi|>",
|
| 711 |
"single_word": false,
|
| 712 |
"lstrip": false,
|
| 713 |
"rstrip": false,
|
| 714 |
-
"normalized": false
|
| 715 |
-
"special": true
|
| 716 |
},
|
| 717 |
{
|
| 718 |
"id": 50335,
|
|
|
|
| 719 |
"content": "<|lo|>",
|
| 720 |
"single_word": false,
|
| 721 |
"lstrip": false,
|
| 722 |
"rstrip": false,
|
| 723 |
-
"normalized": false
|
| 724 |
-
"special": true
|
| 725 |
},
|
| 726 |
{
|
| 727 |
"id": 50336,
|
|
|
|
| 728 |
"content": "<|uz|>",
|
| 729 |
"single_word": false,
|
| 730 |
"lstrip": false,
|
| 731 |
"rstrip": false,
|
| 732 |
-
"normalized": false
|
| 733 |
-
"special": true
|
| 734 |
},
|
| 735 |
{
|
| 736 |
"id": 50337,
|
|
|
|
| 737 |
"content": "<|fo|>",
|
| 738 |
"single_word": false,
|
| 739 |
"lstrip": false,
|
| 740 |
"rstrip": false,
|
| 741 |
-
"normalized": false
|
| 742 |
-
"special": true
|
| 743 |
},
|
| 744 |
{
|
| 745 |
"id": 50338,
|
|
|
|
| 746 |
"content": "<|ht|>",
|
| 747 |
"single_word": false,
|
| 748 |
"lstrip": false,
|
| 749 |
"rstrip": false,
|
| 750 |
-
"normalized": false
|
| 751 |
-
"special": true
|
| 752 |
},
|
| 753 |
{
|
| 754 |
"id": 50339,
|
|
|
|
| 755 |
"content": "<|ps|>",
|
| 756 |
"single_word": false,
|
| 757 |
"lstrip": false,
|
| 758 |
"rstrip": false,
|
| 759 |
-
"normalized": false
|
| 760 |
-
"special": true
|
| 761 |
},
|
| 762 |
{
|
| 763 |
"id": 50340,
|
|
|
|
| 764 |
"content": "<|tk|>",
|
| 765 |
"single_word": false,
|
| 766 |
"lstrip": false,
|
| 767 |
"rstrip": false,
|
| 768 |
-
"normalized": false
|
| 769 |
-
"special": true
|
| 770 |
},
|
| 771 |
{
|
| 772 |
"id": 50341,
|
|
|
|
| 773 |
"content": "<|nn|>",
|
| 774 |
"single_word": false,
|
| 775 |
"lstrip": false,
|
| 776 |
"rstrip": false,
|
| 777 |
-
"normalized": false
|
| 778 |
-
"special": true
|
| 779 |
},
|
| 780 |
{
|
| 781 |
"id": 50342,
|
|
|
|
| 782 |
"content": "<|mt|>",
|
| 783 |
"single_word": false,
|
| 784 |
"lstrip": false,
|
| 785 |
"rstrip": false,
|
| 786 |
-
"normalized": false
|
| 787 |
-
"special": true
|
| 788 |
},
|
| 789 |
{
|
| 790 |
"id": 50343,
|
|
|
|
| 791 |
"content": "<|sa|>",
|
| 792 |
"single_word": false,
|
| 793 |
"lstrip": false,
|
| 794 |
"rstrip": false,
|
| 795 |
-
"normalized": false
|
| 796 |
-
"special": true
|
| 797 |
},
|
| 798 |
{
|
| 799 |
"id": 50344,
|
|
|
|
| 800 |
"content": "<|lb|>",
|
| 801 |
"single_word": false,
|
| 802 |
"lstrip": false,
|
| 803 |
"rstrip": false,
|
| 804 |
-
"normalized": false
|
| 805 |
-
"special": true
|
| 806 |
},
|
| 807 |
{
|
| 808 |
"id": 50345,
|
|
|
|
| 809 |
"content": "<|my|>",
|
| 810 |
"single_word": false,
|
| 811 |
"lstrip": false,
|
| 812 |
"rstrip": false,
|
| 813 |
-
"normalized": false
|
| 814 |
-
"special": true
|
| 815 |
},
|
| 816 |
{
|
| 817 |
"id": 50346,
|
|
|
|
| 818 |
"content": "<|bo|>",
|
| 819 |
"single_word": false,
|
| 820 |
"lstrip": false,
|
| 821 |
"rstrip": false,
|
| 822 |
-
"normalized": false
|
| 823 |
-
"special": true
|
| 824 |
},
|
| 825 |
{
|
| 826 |
"id": 50347,
|
|
|
|
| 827 |
"content": "<|tl|>",
|
| 828 |
"single_word": false,
|
| 829 |
"lstrip": false,
|
| 830 |
"rstrip": false,
|
| 831 |
-
"normalized": false
|
| 832 |
-
"special": true
|
| 833 |
},
|
| 834 |
{
|
| 835 |
"id": 50348,
|
|
|
|
| 836 |
"content": "<|mg|>",
|
| 837 |
"single_word": false,
|
| 838 |
"lstrip": false,
|
| 839 |
"rstrip": false,
|
| 840 |
-
"normalized": false
|
| 841 |
-
"special": true
|
| 842 |
},
|
| 843 |
{
|
| 844 |
"id": 50349,
|
|
|
|
| 845 |
"content": "<|as|>",
|
| 846 |
"single_word": false,
|
| 847 |
"lstrip": false,
|
| 848 |
"rstrip": false,
|
| 849 |
-
"normalized": false
|
| 850 |
-
"special": true
|
| 851 |
},
|
| 852 |
{
|
| 853 |
"id": 50350,
|
|
|
|
| 854 |
"content": "<|tt|>",
|
| 855 |
"single_word": false,
|
| 856 |
"lstrip": false,
|
| 857 |
"rstrip": false,
|
| 858 |
-
"normalized": false
|
| 859 |
-
"special": true
|
| 860 |
},
|
| 861 |
{
|
| 862 |
"id": 50351,
|
|
|
|
| 863 |
"content": "<|haw|>",
|
| 864 |
"single_word": false,
|
| 865 |
"lstrip": false,
|
| 866 |
"rstrip": false,
|
| 867 |
-
"normalized": false
|
| 868 |
-
"special": true
|
| 869 |
},
|
| 870 |
{
|
| 871 |
"id": 50352,
|
|
|
|
| 872 |
"content": "<|ln|>",
|
| 873 |
"single_word": false,
|
| 874 |
"lstrip": false,
|
| 875 |
"rstrip": false,
|
| 876 |
-
"normalized": false
|
| 877 |
-
"special": true
|
| 878 |
},
|
| 879 |
{
|
| 880 |
"id": 50353,
|
|
|
|
| 881 |
"content": "<|ha|>",
|
| 882 |
"single_word": false,
|
| 883 |
"lstrip": false,
|
| 884 |
"rstrip": false,
|
| 885 |
-
"normalized": false
|
| 886 |
-
"special": true
|
| 887 |
},
|
| 888 |
{
|
| 889 |
"id": 50354,
|
|
|
|
| 890 |
"content": "<|ba|>",
|
| 891 |
"single_word": false,
|
| 892 |
"lstrip": false,
|
| 893 |
"rstrip": false,
|
| 894 |
-
"normalized": false
|
| 895 |
-
"special": true
|
| 896 |
},
|
| 897 |
{
|
| 898 |
"id": 50355,
|
|
|
|
| 899 |
"content": "<|jw|>",
|
| 900 |
"single_word": false,
|
| 901 |
"lstrip": false,
|
| 902 |
"rstrip": false,
|
| 903 |
-
"normalized": false
|
| 904 |
-
"special": true
|
| 905 |
},
|
| 906 |
{
|
| 907 |
"id": 50356,
|
|
|
|
| 908 |
"content": "<|su|>",
|
| 909 |
"single_word": false,
|
| 910 |
"lstrip": false,
|
| 911 |
"rstrip": false,
|
| 912 |
-
"normalized": false
|
| 913 |
-
"special": true
|
| 914 |
},
|
| 915 |
{
|
| 916 |
"id": 50357,
|
|
|
|
| 917 |
"content": "<|translate|>",
|
| 918 |
"single_word": false,
|
| 919 |
"lstrip": false,
|
| 920 |
"rstrip": false,
|
| 921 |
-
"normalized": false
|
| 922 |
-
"special": true
|
| 923 |
},
|
| 924 |
{
|
| 925 |
"id": 50358,
|
|
|
|
| 926 |
"content": "<|transcribe|>",
|
| 927 |
"single_word": false,
|
| 928 |
"lstrip": false,
|
| 929 |
"rstrip": false,
|
| 930 |
-
"normalized": false
|
| 931 |
-
"special": true
|
| 932 |
},
|
| 933 |
{
|
| 934 |
"id": 50359,
|
|
|
|
| 935 |
"content": "<|startoflm|>",
|
| 936 |
"single_word": false,
|
| 937 |
"lstrip": false,
|
| 938 |
"rstrip": false,
|
| 939 |
-
"normalized": false
|
| 940 |
-
"special": true
|
| 941 |
},
|
| 942 |
{
|
| 943 |
"id": 50360,
|
|
|
|
| 944 |
"content": "<|startofprev|>",
|
| 945 |
"single_word": false,
|
| 946 |
"lstrip": false,
|
| 947 |
"rstrip": false,
|
| 948 |
-
"normalized": false
|
| 949 |
-
"special": true
|
| 950 |
},
|
| 951 |
{
|
| 952 |
"id": 50361,
|
|
|
|
| 953 |
"content": "<|nocaptions|>",
|
| 954 |
"single_word": false,
|
| 955 |
"lstrip": false,
|
| 956 |
"rstrip": false,
|
| 957 |
-
"normalized": false
|
| 958 |
-
"special": true
|
| 959 |
},
|
| 960 |
{
|
| 961 |
"id": 50362,
|
|
|
|
| 962 |
"content": "<|notimestamps|>",
|
| 963 |
"single_word": false,
|
| 964 |
"lstrip": false,
|
| 965 |
"rstrip": false,
|
| 966 |
-
"normalized": false
|
| 967 |
-
"special": true
|
| 968 |
}
|
| 969 |
],
|
| 970 |
"normalizer": null,
|
| 971 |
"pre_tokenizer": {
|
| 972 |
"type": "ByteLevel",
|
| 973 |
"add_prefix_space": false,
|
| 974 |
-
"trim_offsets": true
|
| 975 |
-
"use_regex": true
|
| 976 |
},
|
| 977 |
"post_processor": {
|
| 978 |
"type": "TemplateProcessing",
|
|
@@ -1067,8 +1066,7 @@
|
|
| 1067 |
"decoder": {
|
| 1068 |
"type": "ByteLevel",
|
| 1069 |
"add_prefix_space": true,
|
| 1070 |
-
"trim_offsets": true
|
| 1071 |
-
"use_regex": true
|
| 1072 |
},
|
| 1073 |
"model": {
|
| 1074 |
"type": "BPE",
|
|
|
|
| 5 |
"added_tokens": [
|
| 6 |
{
|
| 7 |
"id": 50256,
|
| 8 |
+
"special": true,
|
| 9 |
"content": "<|endoftext|>",
|
| 10 |
"single_word": false,
|
| 11 |
"lstrip": false,
|
| 12 |
"rstrip": false,
|
| 13 |
+
"normalized": false
|
|
|
|
| 14 |
},
|
| 15 |
{
|
| 16 |
"id": 50257,
|
| 17 |
+
"special": true,
|
| 18 |
"content": "<|startoftranscript|>",
|
| 19 |
"single_word": false,
|
| 20 |
"lstrip": false,
|
| 21 |
"rstrip": false,
|
| 22 |
+
"normalized": false
|
|
|
|
| 23 |
},
|
| 24 |
{
|
| 25 |
"id": 50258,
|
| 26 |
+
"special": true,
|
| 27 |
"content": "<|en|>",
|
| 28 |
"single_word": false,
|
| 29 |
"lstrip": false,
|
| 30 |
"rstrip": false,
|
| 31 |
+
"normalized": false
|
|
|
|
| 32 |
},
|
| 33 |
{
|
| 34 |
"id": 50259,
|
| 35 |
+
"special": true,
|
| 36 |
"content": "<|zh|>",
|
| 37 |
"single_word": false,
|
| 38 |
"lstrip": false,
|
| 39 |
"rstrip": false,
|
| 40 |
+
"normalized": false
|
|
|
|
| 41 |
},
|
| 42 |
{
|
| 43 |
"id": 50260,
|
| 44 |
+
"special": true,
|
| 45 |
"content": "<|de|>",
|
| 46 |
"single_word": false,
|
| 47 |
"lstrip": false,
|
| 48 |
"rstrip": false,
|
| 49 |
+
"normalized": false
|
|
|
|
| 50 |
},
|
| 51 |
{
|
| 52 |
"id": 50261,
|
| 53 |
+
"special": true,
|
| 54 |
"content": "<|es|>",
|
| 55 |
"single_word": false,
|
| 56 |
"lstrip": false,
|
| 57 |
"rstrip": false,
|
| 58 |
+
"normalized": false
|
|
|
|
| 59 |
},
|
| 60 |
{
|
| 61 |
"id": 50262,
|
| 62 |
+
"special": true,
|
| 63 |
"content": "<|ru|>",
|
| 64 |
"single_word": false,
|
| 65 |
"lstrip": false,
|
| 66 |
"rstrip": false,
|
| 67 |
+
"normalized": false
|
|
|
|
| 68 |
},
|
| 69 |
{
|
| 70 |
"id": 50263,
|
| 71 |
+
"special": true,
|
| 72 |
"content": "<|ko|>",
|
| 73 |
"single_word": false,
|
| 74 |
"lstrip": false,
|
| 75 |
"rstrip": false,
|
| 76 |
+
"normalized": false
|
|
|
|
| 77 |
},
|
| 78 |
{
|
| 79 |
"id": 50264,
|
| 80 |
+
"special": true,
|
| 81 |
"content": "<|fr|>",
|
| 82 |
"single_word": false,
|
| 83 |
"lstrip": false,
|
| 84 |
"rstrip": false,
|
| 85 |
+
"normalized": false
|
|
|
|
| 86 |
},
|
| 87 |
{
|
| 88 |
"id": 50265,
|
| 89 |
+
"special": true,
|
| 90 |
"content": "<|ja|>",
|
| 91 |
"single_word": false,
|
| 92 |
"lstrip": false,
|
| 93 |
"rstrip": false,
|
| 94 |
+
"normalized": false
|
|
|
|
| 95 |
},
|
| 96 |
{
|
| 97 |
"id": 50266,
|
| 98 |
+
"special": true,
|
| 99 |
"content": "<|pt|>",
|
| 100 |
"single_word": false,
|
| 101 |
"lstrip": false,
|
| 102 |
"rstrip": false,
|
| 103 |
+
"normalized": false
|
|
|
|
| 104 |
},
|
| 105 |
{
|
| 106 |
"id": 50267,
|
| 107 |
+
"special": true,
|
| 108 |
"content": "<|tr|>",
|
| 109 |
"single_word": false,
|
| 110 |
"lstrip": false,
|
| 111 |
"rstrip": false,
|
| 112 |
+
"normalized": false
|
|
|
|
| 113 |
},
|
| 114 |
{
|
| 115 |
"id": 50268,
|
| 116 |
+
"special": true,
|
| 117 |
"content": "<|pl|>",
|
| 118 |
"single_word": false,
|
| 119 |
"lstrip": false,
|
| 120 |
"rstrip": false,
|
| 121 |
+
"normalized": false
|
|
|
|
| 122 |
},
|
| 123 |
{
|
| 124 |
"id": 50269,
|
| 125 |
+
"special": true,
|
| 126 |
"content": "<|ca|>",
|
| 127 |
"single_word": false,
|
| 128 |
"lstrip": false,
|
| 129 |
"rstrip": false,
|
| 130 |
+
"normalized": false
|
|
|
|
| 131 |
},
|
| 132 |
{
|
| 133 |
"id": 50270,
|
| 134 |
+
"special": true,
|
| 135 |
"content": "<|nl|>",
|
| 136 |
"single_word": false,
|
| 137 |
"lstrip": false,
|
| 138 |
"rstrip": false,
|
| 139 |
+
"normalized": false
|
|
|
|
| 140 |
},
|
| 141 |
{
|
| 142 |
"id": 50271,
|
| 143 |
+
"special": true,
|
| 144 |
"content": "<|ar|>",
|
| 145 |
"single_word": false,
|
| 146 |
"lstrip": false,
|
| 147 |
"rstrip": false,
|
| 148 |
+
"normalized": false
|
|
|
|
| 149 |
},
|
| 150 |
{
|
| 151 |
"id": 50272,
|
| 152 |
+
"special": true,
|
| 153 |
"content": "<|sv|>",
|
| 154 |
"single_word": false,
|
| 155 |
"lstrip": false,
|
| 156 |
"rstrip": false,
|
| 157 |
+
"normalized": false
|
|
|
|
| 158 |
},
|
| 159 |
{
|
| 160 |
"id": 50273,
|
| 161 |
+
"special": true,
|
| 162 |
"content": "<|it|>",
|
| 163 |
"single_word": false,
|
| 164 |
"lstrip": false,
|
| 165 |
"rstrip": false,
|
| 166 |
+
"normalized": false
|
|
|
|
| 167 |
},
|
| 168 |
{
|
| 169 |
"id": 50274,
|
| 170 |
+
"special": true,
|
| 171 |
"content": "<|id|>",
|
| 172 |
"single_word": false,
|
| 173 |
"lstrip": false,
|
| 174 |
"rstrip": false,
|
| 175 |
+
"normalized": false
|
|
|
|
| 176 |
},
|
| 177 |
{
|
| 178 |
"id": 50275,
|
| 179 |
+
"special": true,
|
| 180 |
"content": "<|hi|>",
|
| 181 |
"single_word": false,
|
| 182 |
"lstrip": false,
|
| 183 |
"rstrip": false,
|
| 184 |
+
"normalized": false
|
|
|
|
| 185 |
},
|
| 186 |
{
|
| 187 |
"id": 50276,
|
| 188 |
+
"special": true,
|
| 189 |
"content": "<|fi|>",
|
| 190 |
"single_word": false,
|
| 191 |
"lstrip": false,
|
| 192 |
"rstrip": false,
|
| 193 |
+
"normalized": false
|
|
|
|
| 194 |
},
|
| 195 |
{
|
| 196 |
"id": 50277,
|
| 197 |
+
"special": true,
|
| 198 |
"content": "<|vi|>",
|
| 199 |
"single_word": false,
|
| 200 |
"lstrip": false,
|
| 201 |
"rstrip": false,
|
| 202 |
+
"normalized": false
|
|
|
|
| 203 |
},
|
| 204 |
{
|
| 205 |
"id": 50278,
|
| 206 |
+
"special": true,
|
| 207 |
"content": "<|iw|>",
|
| 208 |
"single_word": false,
|
| 209 |
"lstrip": false,
|
| 210 |
"rstrip": false,
|
| 211 |
+
"normalized": false
|
|
|
|
| 212 |
},
|
| 213 |
{
|
| 214 |
"id": 50279,
|
| 215 |
+
"special": true,
|
| 216 |
"content": "<|uk|>",
|
| 217 |
"single_word": false,
|
| 218 |
"lstrip": false,
|
| 219 |
"rstrip": false,
|
| 220 |
+
"normalized": false
|
|
|
|
| 221 |
},
|
| 222 |
{
|
| 223 |
"id": 50280,
|
| 224 |
+
"special": true,
|
| 225 |
"content": "<|el|>",
|
| 226 |
"single_word": false,
|
| 227 |
"lstrip": false,
|
| 228 |
"rstrip": false,
|
| 229 |
+
"normalized": false
|
|
|
|
| 230 |
},
|
| 231 |
{
|
| 232 |
"id": 50281,
|
| 233 |
+
"special": true,
|
| 234 |
"content": "<|ms|>",
|
| 235 |
"single_word": false,
|
| 236 |
"lstrip": false,
|
| 237 |
"rstrip": false,
|
| 238 |
+
"normalized": false
|
|
|
|
| 239 |
},
|
| 240 |
{
|
| 241 |
"id": 50282,
|
| 242 |
+
"special": true,
|
| 243 |
"content": "<|cs|>",
|
| 244 |
"single_word": false,
|
| 245 |
"lstrip": false,
|
| 246 |
"rstrip": false,
|
| 247 |
+
"normalized": false
|
|
|
|
| 248 |
},
|
| 249 |
{
|
| 250 |
"id": 50283,
|
| 251 |
+
"special": true,
|
| 252 |
"content": "<|ro|>",
|
| 253 |
"single_word": false,
|
| 254 |
"lstrip": false,
|
| 255 |
"rstrip": false,
|
| 256 |
+
"normalized": false
|
|
|
|
| 257 |
},
|
| 258 |
{
|
| 259 |
"id": 50284,
|
| 260 |
+
"special": true,
|
| 261 |
"content": "<|da|>",
|
| 262 |
"single_word": false,
|
| 263 |
"lstrip": false,
|
| 264 |
"rstrip": false,
|
| 265 |
+
"normalized": false
|
|
|
|
| 266 |
},
|
| 267 |
{
|
| 268 |
"id": 50285,
|
| 269 |
+
"special": true,
|
| 270 |
"content": "<|hu|>",
|
| 271 |
"single_word": false,
|
| 272 |
"lstrip": false,
|
| 273 |
"rstrip": false,
|
| 274 |
+
"normalized": false
|
|
|
|
| 275 |
},
|
| 276 |
{
|
| 277 |
"id": 50286,
|
| 278 |
+
"special": true,
|
| 279 |
"content": "<|ta|>",
|
| 280 |
"single_word": false,
|
| 281 |
"lstrip": false,
|
| 282 |
"rstrip": false,
|
| 283 |
+
"normalized": false
|
|
|
|
| 284 |
},
|
| 285 |
{
|
| 286 |
"id": 50287,
|
| 287 |
+
"special": true,
|
| 288 |
"content": "<|no|>",
|
| 289 |
"single_word": false,
|
| 290 |
"lstrip": false,
|
| 291 |
"rstrip": false,
|
| 292 |
+
"normalized": false
|
|
|
|
| 293 |
},
|
| 294 |
{
|
| 295 |
"id": 50288,
|
| 296 |
+
"special": true,
|
| 297 |
"content": "<|th|>",
|
| 298 |
"single_word": false,
|
| 299 |
"lstrip": false,
|
| 300 |
"rstrip": false,
|
| 301 |
+
"normalized": false
|
|
|
|
| 302 |
},
|
| 303 |
{
|
| 304 |
"id": 50289,
|
| 305 |
+
"special": true,
|
| 306 |
"content": "<|ur|>",
|
| 307 |
"single_word": false,
|
| 308 |
"lstrip": false,
|
| 309 |
"rstrip": false,
|
| 310 |
+
"normalized": false
|
|
|
|
| 311 |
},
|
| 312 |
{
|
| 313 |
"id": 50290,
|
| 314 |
+
"special": true,
|
| 315 |
"content": "<|hr|>",
|
| 316 |
"single_word": false,
|
| 317 |
"lstrip": false,
|
| 318 |
"rstrip": false,
|
| 319 |
+
"normalized": false
|
|
|
|
| 320 |
},
|
| 321 |
{
|
| 322 |
"id": 50291,
|
| 323 |
+
"special": true,
|
| 324 |
"content": "<|bg|>",
|
| 325 |
"single_word": false,
|
| 326 |
"lstrip": false,
|
| 327 |
"rstrip": false,
|
| 328 |
+
"normalized": false
|
|
|
|
| 329 |
},
|
| 330 |
{
|
| 331 |
"id": 50292,
|
| 332 |
+
"special": true,
|
| 333 |
"content": "<|lt|>",
|
| 334 |
"single_word": false,
|
| 335 |
"lstrip": false,
|
| 336 |
"rstrip": false,
|
| 337 |
+
"normalized": false
|
|
|
|
| 338 |
},
|
| 339 |
{
|
| 340 |
"id": 50293,
|
| 341 |
+
"special": true,
|
| 342 |
"content": "<|la|>",
|
| 343 |
"single_word": false,
|
| 344 |
"lstrip": false,
|
| 345 |
"rstrip": false,
|
| 346 |
+
"normalized": false
|
|
|
|
| 347 |
},
|
| 348 |
{
|
| 349 |
"id": 50294,
|
| 350 |
+
"special": true,
|
| 351 |
"content": "<|mi|>",
|
| 352 |
"single_word": false,
|
| 353 |
"lstrip": false,
|
| 354 |
"rstrip": false,
|
| 355 |
+
"normalized": false
|
|
|
|
| 356 |
},
|
| 357 |
{
|
| 358 |
"id": 50295,
|
| 359 |
+
"special": true,
|
| 360 |
"content": "<|ml|>",
|
| 361 |
"single_word": false,
|
| 362 |
"lstrip": false,
|
| 363 |
"rstrip": false,
|
| 364 |
+
"normalized": false
|
|
|
|
| 365 |
},
|
| 366 |
{
|
| 367 |
"id": 50296,
|
| 368 |
+
"special": true,
|
| 369 |
"content": "<|cy|>",
|
| 370 |
"single_word": false,
|
| 371 |
"lstrip": false,
|
| 372 |
"rstrip": false,
|
| 373 |
+
"normalized": false
|
|
|
|
| 374 |
},
|
| 375 |
{
|
| 376 |
"id": 50297,
|
| 377 |
+
"special": true,
|
| 378 |
"content": "<|sk|>",
|
| 379 |
"single_word": false,
|
| 380 |
"lstrip": false,
|
| 381 |
"rstrip": false,
|
| 382 |
+
"normalized": false
|
|
|
|
| 383 |
},
|
| 384 |
{
|
| 385 |
"id": 50298,
|
| 386 |
+
"special": true,
|
| 387 |
"content": "<|te|>",
|
| 388 |
"single_word": false,
|
| 389 |
"lstrip": false,
|
| 390 |
"rstrip": false,
|
| 391 |
+
"normalized": false
|
|
|
|
| 392 |
},
|
| 393 |
{
|
| 394 |
"id": 50299,
|
| 395 |
+
"special": true,
|
| 396 |
"content": "<|fa|>",
|
| 397 |
"single_word": false,
|
| 398 |
"lstrip": false,
|
| 399 |
"rstrip": false,
|
| 400 |
+
"normalized": false
|
|
|
|
| 401 |
},
|
| 402 |
{
|
| 403 |
"id": 50300,
|
| 404 |
+
"special": true,
|
| 405 |
"content": "<|lv|>",
|
| 406 |
"single_word": false,
|
| 407 |
"lstrip": false,
|
| 408 |
"rstrip": false,
|
| 409 |
+
"normalized": false
|
|
|
|
| 410 |
},
|
| 411 |
{
|
| 412 |
"id": 50301,
|
| 413 |
+
"special": true,
|
| 414 |
"content": "<|bn|>",
|
| 415 |
"single_word": false,
|
| 416 |
"lstrip": false,
|
| 417 |
"rstrip": false,
|
| 418 |
+
"normalized": false
|
|
|
|
| 419 |
},
|
| 420 |
{
|
| 421 |
"id": 50302,
|
| 422 |
+
"special": true,
|
| 423 |
"content": "<|sr|>",
|
| 424 |
"single_word": false,
|
| 425 |
"lstrip": false,
|
| 426 |
"rstrip": false,
|
| 427 |
+
"normalized": false
|
|
|
|
| 428 |
},
|
| 429 |
{
|
| 430 |
"id": 50303,
|
| 431 |
+
"special": true,
|
| 432 |
"content": "<|az|>",
|
| 433 |
"single_word": false,
|
| 434 |
"lstrip": false,
|
| 435 |
"rstrip": false,
|
| 436 |
+
"normalized": false
|
|
|
|
| 437 |
},
|
| 438 |
{
|
| 439 |
"id": 50304,
|
| 440 |
+
"special": true,
|
| 441 |
"content": "<|sl|>",
|
| 442 |
"single_word": false,
|
| 443 |
"lstrip": false,
|
| 444 |
"rstrip": false,
|
| 445 |
+
"normalized": false
|
|
|
|
| 446 |
},
|
| 447 |
{
|
| 448 |
"id": 50305,
|
| 449 |
+
"special": true,
|
| 450 |
"content": "<|kn|>",
|
| 451 |
"single_word": false,
|
| 452 |
"lstrip": false,
|
| 453 |
"rstrip": false,
|
| 454 |
+
"normalized": false
|
|
|
|
| 455 |
},
|
| 456 |
{
|
| 457 |
"id": 50306,
|
| 458 |
+
"special": true,
|
| 459 |
"content": "<|et|>",
|
| 460 |
"single_word": false,
|
| 461 |
"lstrip": false,
|
| 462 |
"rstrip": false,
|
| 463 |
+
"normalized": false
|
|
|
|
| 464 |
},
|
| 465 |
{
|
| 466 |
"id": 50307,
|
| 467 |
+
"special": true,
|
| 468 |
"content": "<|mk|>",
|
| 469 |
"single_word": false,
|
| 470 |
"lstrip": false,
|
| 471 |
"rstrip": false,
|
| 472 |
+
"normalized": false
|
|
|
|
| 473 |
},
|
| 474 |
{
|
| 475 |
"id": 50308,
|
| 476 |
+
"special": true,
|
| 477 |
"content": "<|br|>",
|
| 478 |
"single_word": false,
|
| 479 |
"lstrip": false,
|
| 480 |
"rstrip": false,
|
| 481 |
+
"normalized": false
|
|
|
|
| 482 |
},
|
| 483 |
{
|
| 484 |
"id": 50309,
|
| 485 |
+
"special": true,
|
| 486 |
"content": "<|eu|>",
|
| 487 |
"single_word": false,
|
| 488 |
"lstrip": false,
|
| 489 |
"rstrip": false,
|
| 490 |
+
"normalized": false
|
|
|
|
| 491 |
},
|
| 492 |
{
|
| 493 |
"id": 50310,
|
| 494 |
+
"special": true,
|
| 495 |
"content": "<|is|>",
|
| 496 |
"single_word": false,
|
| 497 |
"lstrip": false,
|
| 498 |
"rstrip": false,
|
| 499 |
+
"normalized": false
|
|
|
|
| 500 |
},
|
| 501 |
{
|
| 502 |
"id": 50311,
|
| 503 |
+
"special": true,
|
| 504 |
"content": "<|hy|>",
|
| 505 |
"single_word": false,
|
| 506 |
"lstrip": false,
|
| 507 |
"rstrip": false,
|
| 508 |
+
"normalized": false
|
|
|
|
| 509 |
},
|
| 510 |
{
|
| 511 |
"id": 50312,
|
| 512 |
+
"special": true,
|
| 513 |
"content": "<|ne|>",
|
| 514 |
"single_word": false,
|
| 515 |
"lstrip": false,
|
| 516 |
"rstrip": false,
|
| 517 |
+
"normalized": false
|
|
|
|
| 518 |
},
|
| 519 |
{
|
| 520 |
"id": 50313,
|
| 521 |
+
"special": true,
|
| 522 |
"content": "<|mn|>",
|
| 523 |
"single_word": false,
|
| 524 |
"lstrip": false,
|
| 525 |
"rstrip": false,
|
| 526 |
+
"normalized": false
|
|
|
|
| 527 |
},
|
| 528 |
{
|
| 529 |
"id": 50314,
|
| 530 |
+
"special": true,
|
| 531 |
"content": "<|bs|>",
|
| 532 |
"single_word": false,
|
| 533 |
"lstrip": false,
|
| 534 |
"rstrip": false,
|
| 535 |
+
"normalized": false
|
|
|
|
| 536 |
},
|
| 537 |
{
|
| 538 |
"id": 50315,
|
| 539 |
+
"special": true,
|
| 540 |
"content": "<|kk|>",
|
| 541 |
"single_word": false,
|
| 542 |
"lstrip": false,
|
| 543 |
"rstrip": false,
|
| 544 |
+
"normalized": false
|
|
|
|
| 545 |
},
|
| 546 |
{
|
| 547 |
"id": 50316,
|
| 548 |
+
"special": true,
|
| 549 |
"content": "<|sq|>",
|
| 550 |
"single_word": false,
|
| 551 |
"lstrip": false,
|
| 552 |
"rstrip": false,
|
| 553 |
+
"normalized": false
|
|
|
|
| 554 |
},
|
| 555 |
{
|
| 556 |
"id": 50317,
|
| 557 |
+
"special": true,
|
| 558 |
"content": "<|sw|>",
|
| 559 |
"single_word": false,
|
| 560 |
"lstrip": false,
|
| 561 |
"rstrip": false,
|
| 562 |
+
"normalized": false
|
|
|
|
| 563 |
},
|
| 564 |
{
|
| 565 |
"id": 50318,
|
| 566 |
+
"special": true,
|
| 567 |
"content": "<|gl|>",
|
| 568 |
"single_word": false,
|
| 569 |
"lstrip": false,
|
| 570 |
"rstrip": false,
|
| 571 |
+
"normalized": false
|
|
|
|
| 572 |
},
|
| 573 |
{
|
| 574 |
"id": 50319,
|
| 575 |
+
"special": true,
|
| 576 |
"content": "<|mr|>",
|
| 577 |
"single_word": false,
|
| 578 |
"lstrip": false,
|
| 579 |
"rstrip": false,
|
| 580 |
+
"normalized": false
|
|
|
|
| 581 |
},
|
| 582 |
{
|
| 583 |
"id": 50320,
|
| 584 |
+
"special": true,
|
| 585 |
"content": "<|pa|>",
|
| 586 |
"single_word": false,
|
| 587 |
"lstrip": false,
|
| 588 |
"rstrip": false,
|
| 589 |
+
"normalized": false
|
|
|
|
| 590 |
},
|
| 591 |
{
|
| 592 |
"id": 50321,
|
| 593 |
+
"special": true,
|
| 594 |
"content": "<|si|>",
|
| 595 |
"single_word": false,
|
| 596 |
"lstrip": false,
|
| 597 |
"rstrip": false,
|
| 598 |
+
"normalized": false
|
|
|
|
| 599 |
},
|
| 600 |
{
|
| 601 |
"id": 50322,
|
| 602 |
+
"special": true,
|
| 603 |
"content": "<|km|>",
|
| 604 |
"single_word": false,
|
| 605 |
"lstrip": false,
|
| 606 |
"rstrip": false,
|
| 607 |
+
"normalized": false
|
|
|
|
| 608 |
},
|
| 609 |
{
|
| 610 |
"id": 50323,
|
| 611 |
+
"special": true,
|
| 612 |
"content": "<|sn|>",
|
| 613 |
"single_word": false,
|
| 614 |
"lstrip": false,
|
| 615 |
"rstrip": false,
|
| 616 |
+
"normalized": false
|
|
|
|
| 617 |
},
|
| 618 |
{
|
| 619 |
"id": 50324,
|
| 620 |
+
"special": true,
|
| 621 |
"content": "<|yo|>",
|
| 622 |
"single_word": false,
|
| 623 |
"lstrip": false,
|
| 624 |
"rstrip": false,
|
| 625 |
+
"normalized": false
|
|
|
|
| 626 |
},
|
| 627 |
{
|
| 628 |
"id": 50325,
|
| 629 |
+
"special": true,
|
| 630 |
"content": "<|so|>",
|
| 631 |
"single_word": false,
|
| 632 |
"lstrip": false,
|
| 633 |
"rstrip": false,
|
| 634 |
+
"normalized": false
|
|
|
|
| 635 |
},
|
| 636 |
{
|
| 637 |
"id": 50326,
|
| 638 |
+
"special": true,
|
| 639 |
"content": "<|af|>",
|
| 640 |
"single_word": false,
|
| 641 |
"lstrip": false,
|
| 642 |
"rstrip": false,
|
| 643 |
+
"normalized": false
|
|
|
|
| 644 |
},
|
| 645 |
{
|
| 646 |
"id": 50327,
|
| 647 |
+
"special": true,
|
| 648 |
"content": "<|oc|>",
|
| 649 |
"single_word": false,
|
| 650 |
"lstrip": false,
|
| 651 |
"rstrip": false,
|
| 652 |
+
"normalized": false
|
|
|
|
| 653 |
},
|
| 654 |
{
|
| 655 |
"id": 50328,
|
| 656 |
+
"special": true,
|
| 657 |
"content": "<|ka|>",
|
| 658 |
"single_word": false,
|
| 659 |
"lstrip": false,
|
| 660 |
"rstrip": false,
|
| 661 |
+
"normalized": false
|
|
|
|
| 662 |
},
|
| 663 |
{
|
| 664 |
"id": 50329,
|
| 665 |
+
"special": true,
|
| 666 |
"content": "<|be|>",
|
| 667 |
"single_word": false,
|
| 668 |
"lstrip": false,
|
| 669 |
"rstrip": false,
|
| 670 |
+
"normalized": false
|
|
|
|
| 671 |
},
|
| 672 |
{
|
| 673 |
"id": 50330,
|
| 674 |
+
"special": true,
|
| 675 |
"content": "<|tg|>",
|
| 676 |
"single_word": false,
|
| 677 |
"lstrip": false,
|
| 678 |
"rstrip": false,
|
| 679 |
+
"normalized": false
|
|
|
|
| 680 |
},
|
| 681 |
{
|
| 682 |
"id": 50331,
|
| 683 |
+
"special": true,
|
| 684 |
"content": "<|sd|>",
|
| 685 |
"single_word": false,
|
| 686 |
"lstrip": false,
|
| 687 |
"rstrip": false,
|
| 688 |
+
"normalized": false
|
|
|
|
| 689 |
},
|
| 690 |
{
|
| 691 |
"id": 50332,
|
| 692 |
+
"special": true,
|
| 693 |
"content": "<|gu|>",
|
| 694 |
"single_word": false,
|
| 695 |
"lstrip": false,
|
| 696 |
"rstrip": false,
|
| 697 |
+
"normalized": false
|
|
|
|
| 698 |
},
|
| 699 |
{
|
| 700 |
"id": 50333,
|
| 701 |
+
"special": true,
|
| 702 |
"content": "<|am|>",
|
| 703 |
"single_word": false,
|
| 704 |
"lstrip": false,
|
| 705 |
"rstrip": false,
|
| 706 |
+
"normalized": false
|
|
|
|
| 707 |
},
|
| 708 |
{
|
| 709 |
"id": 50334,
|
| 710 |
+
"special": true,
|
| 711 |
"content": "<|yi|>",
|
| 712 |
"single_word": false,
|
| 713 |
"lstrip": false,
|
| 714 |
"rstrip": false,
|
| 715 |
+
"normalized": false
|
|
|
|
| 716 |
},
|
| 717 |
{
|
| 718 |
"id": 50335,
|
| 719 |
+
"special": true,
|
| 720 |
"content": "<|lo|>",
|
| 721 |
"single_word": false,
|
| 722 |
"lstrip": false,
|
| 723 |
"rstrip": false,
|
| 724 |
+
"normalized": false
|
|
|
|
| 725 |
},
|
| 726 |
{
|
| 727 |
"id": 50336,
|
| 728 |
+
"special": true,
|
| 729 |
"content": "<|uz|>",
|
| 730 |
"single_word": false,
|
| 731 |
"lstrip": false,
|
| 732 |
"rstrip": false,
|
| 733 |
+
"normalized": false
|
|
|
|
| 734 |
},
|
| 735 |
{
|
| 736 |
"id": 50337,
|
| 737 |
+
"special": true,
|
| 738 |
"content": "<|fo|>",
|
| 739 |
"single_word": false,
|
| 740 |
"lstrip": false,
|
| 741 |
"rstrip": false,
|
| 742 |
+
"normalized": false
|
|
|
|
| 743 |
},
|
| 744 |
{
|
| 745 |
"id": 50338,
|
| 746 |
+
"special": true,
|
| 747 |
"content": "<|ht|>",
|
| 748 |
"single_word": false,
|
| 749 |
"lstrip": false,
|
| 750 |
"rstrip": false,
|
| 751 |
+
"normalized": false
|
|
|
|
| 752 |
},
|
| 753 |
{
|
| 754 |
"id": 50339,
|
| 755 |
+
"special": true,
|
| 756 |
"content": "<|ps|>",
|
| 757 |
"single_word": false,
|
| 758 |
"lstrip": false,
|
| 759 |
"rstrip": false,
|
| 760 |
+
"normalized": false
|
|
|
|
| 761 |
},
|
| 762 |
{
|
| 763 |
"id": 50340,
|
| 764 |
+
"special": true,
|
| 765 |
"content": "<|tk|>",
|
| 766 |
"single_word": false,
|
| 767 |
"lstrip": false,
|
| 768 |
"rstrip": false,
|
| 769 |
+
"normalized": false
|
|
|
|
| 770 |
},
|
| 771 |
{
|
| 772 |
"id": 50341,
|
| 773 |
+
"special": true,
|
| 774 |
"content": "<|nn|>",
|
| 775 |
"single_word": false,
|
| 776 |
"lstrip": false,
|
| 777 |
"rstrip": false,
|
| 778 |
+
"normalized": false
|
|
|
|
| 779 |
},
|
| 780 |
{
|
| 781 |
"id": 50342,
|
| 782 |
+
"special": true,
|
| 783 |
"content": "<|mt|>",
|
| 784 |
"single_word": false,
|
| 785 |
"lstrip": false,
|
| 786 |
"rstrip": false,
|
| 787 |
+
"normalized": false
|
|
|
|
| 788 |
},
|
| 789 |
{
|
| 790 |
"id": 50343,
|
| 791 |
+
"special": true,
|
| 792 |
"content": "<|sa|>",
|
| 793 |
"single_word": false,
|
| 794 |
"lstrip": false,
|
| 795 |
"rstrip": false,
|
| 796 |
+
"normalized": false
|
|
|
|
| 797 |
},
|
| 798 |
{
|
| 799 |
"id": 50344,
|
| 800 |
+
"special": true,
|
| 801 |
"content": "<|lb|>",
|
| 802 |
"single_word": false,
|
| 803 |
"lstrip": false,
|
| 804 |
"rstrip": false,
|
| 805 |
+
"normalized": false
|
|
|
|
| 806 |
},
|
| 807 |
{
|
| 808 |
"id": 50345,
|
| 809 |
+
"special": true,
|
| 810 |
"content": "<|my|>",
|
| 811 |
"single_word": false,
|
| 812 |
"lstrip": false,
|
| 813 |
"rstrip": false,
|
| 814 |
+
"normalized": false
|
|
|
|
| 815 |
},
|
| 816 |
{
|
| 817 |
"id": 50346,
|
| 818 |
+
"special": true,
|
| 819 |
"content": "<|bo|>",
|
| 820 |
"single_word": false,
|
| 821 |
"lstrip": false,
|
| 822 |
"rstrip": false,
|
| 823 |
+
"normalized": false
|
|
|
|
| 824 |
},
|
| 825 |
{
|
| 826 |
"id": 50347,
|
| 827 |
+
"special": true,
|
| 828 |
"content": "<|tl|>",
|
| 829 |
"single_word": false,
|
| 830 |
"lstrip": false,
|
| 831 |
"rstrip": false,
|
| 832 |
+
"normalized": false
|
|
|
|
| 833 |
},
|
| 834 |
{
|
| 835 |
"id": 50348,
|
| 836 |
+
"special": true,
|
| 837 |
"content": "<|mg|>",
|
| 838 |
"single_word": false,
|
| 839 |
"lstrip": false,
|
| 840 |
"rstrip": false,
|
| 841 |
+
"normalized": false
|
|
|
|
| 842 |
},
|
| 843 |
{
|
| 844 |
"id": 50349,
|
| 845 |
+
"special": true,
|
| 846 |
"content": "<|as|>",
|
| 847 |
"single_word": false,
|
| 848 |
"lstrip": false,
|
| 849 |
"rstrip": false,
|
| 850 |
+
"normalized": false
|
|
|
|
| 851 |
},
|
| 852 |
{
|
| 853 |
"id": 50350,
|
| 854 |
+
"special": true,
|
| 855 |
"content": "<|tt|>",
|
| 856 |
"single_word": false,
|
| 857 |
"lstrip": false,
|
| 858 |
"rstrip": false,
|
| 859 |
+
"normalized": false
|
|
|
|
| 860 |
},
|
| 861 |
{
|
| 862 |
"id": 50351,
|
| 863 |
+
"special": true,
|
| 864 |
"content": "<|haw|>",
|
| 865 |
"single_word": false,
|
| 866 |
"lstrip": false,
|
| 867 |
"rstrip": false,
|
| 868 |
+
"normalized": false
|
|
|
|
| 869 |
},
|
| 870 |
{
|
| 871 |
"id": 50352,
|
| 872 |
+
"special": true,
|
| 873 |
"content": "<|ln|>",
|
| 874 |
"single_word": false,
|
| 875 |
"lstrip": false,
|
| 876 |
"rstrip": false,
|
| 877 |
+
"normalized": false
|
|
|
|
| 878 |
},
|
| 879 |
{
|
| 880 |
"id": 50353,
|
| 881 |
+
"special": true,
|
| 882 |
"content": "<|ha|>",
|
| 883 |
"single_word": false,
|
| 884 |
"lstrip": false,
|
| 885 |
"rstrip": false,
|
| 886 |
+
"normalized": false
|
|
|
|
| 887 |
},
|
| 888 |
{
|
| 889 |
"id": 50354,
|
| 890 |
+
"special": true,
|
| 891 |
"content": "<|ba|>",
|
| 892 |
"single_word": false,
|
| 893 |
"lstrip": false,
|
| 894 |
"rstrip": false,
|
| 895 |
+
"normalized": false
|
|
|
|
| 896 |
},
|
| 897 |
{
|
| 898 |
"id": 50355,
|
| 899 |
+
"special": true,
|
| 900 |
"content": "<|jw|>",
|
| 901 |
"single_word": false,
|
| 902 |
"lstrip": false,
|
| 903 |
"rstrip": false,
|
| 904 |
+
"normalized": false
|
|
|
|
| 905 |
},
|
| 906 |
{
|
| 907 |
"id": 50356,
|
| 908 |
+
"special": true,
|
| 909 |
"content": "<|su|>",
|
| 910 |
"single_word": false,
|
| 911 |
"lstrip": false,
|
| 912 |
"rstrip": false,
|
| 913 |
+
"normalized": false
|
|
|
|
| 914 |
},
|
| 915 |
{
|
| 916 |
"id": 50357,
|
| 917 |
+
"special": true,
|
| 918 |
"content": "<|translate|>",
|
| 919 |
"single_word": false,
|
| 920 |
"lstrip": false,
|
| 921 |
"rstrip": false,
|
| 922 |
+
"normalized": false
|
|
|
|
| 923 |
},
|
| 924 |
{
|
| 925 |
"id": 50358,
|
| 926 |
+
"special": true,
|
| 927 |
"content": "<|transcribe|>",
|
| 928 |
"single_word": false,
|
| 929 |
"lstrip": false,
|
| 930 |
"rstrip": false,
|
| 931 |
+
"normalized": false
|
|
|
|
| 932 |
},
|
| 933 |
{
|
| 934 |
"id": 50359,
|
| 935 |
+
"special": true,
|
| 936 |
"content": "<|startoflm|>",
|
| 937 |
"single_word": false,
|
| 938 |
"lstrip": false,
|
| 939 |
"rstrip": false,
|
| 940 |
+
"normalized": false
|
|
|
|
| 941 |
},
|
| 942 |
{
|
| 943 |
"id": 50360,
|
| 944 |
+
"special": true,
|
| 945 |
"content": "<|startofprev|>",
|
| 946 |
"single_word": false,
|
| 947 |
"lstrip": false,
|
| 948 |
"rstrip": false,
|
| 949 |
+
"normalized": false
|
|
|
|
| 950 |
},
|
| 951 |
{
|
| 952 |
"id": 50361,
|
| 953 |
+
"special": true,
|
| 954 |
"content": "<|nocaptions|>",
|
| 955 |
"single_word": false,
|
| 956 |
"lstrip": false,
|
| 957 |
"rstrip": false,
|
| 958 |
+
"normalized": false
|
|
|
|
| 959 |
},
|
| 960 |
{
|
| 961 |
"id": 50362,
|
| 962 |
+
"special": true,
|
| 963 |
"content": "<|notimestamps|>",
|
| 964 |
"single_word": false,
|
| 965 |
"lstrip": false,
|
| 966 |
"rstrip": false,
|
| 967 |
+
"normalized": false
|
|
|
|
| 968 |
}
|
| 969 |
],
|
| 970 |
"normalizer": null,
|
| 971 |
"pre_tokenizer": {
|
| 972 |
"type": "ByteLevel",
|
| 973 |
"add_prefix_space": false,
|
| 974 |
+
"trim_offsets": true
|
|
|
|
| 975 |
},
|
| 976 |
"post_processor": {
|
| 977 |
"type": "TemplateProcessing",
|
|
|
|
| 1066 |
"decoder": {
|
| 1067 |
"type": "ByteLevel",
|
| 1068 |
"add_prefix_space": true,
|
| 1069 |
+
"trim_offsets": true
|
|
|
|
| 1070 |
},
|
| 1071 |
"model": {
|
| 1072 |
"type": "BPE",
|
quantized/openai/whisper-base.en/default/tokenizer_config.json
CHANGED
|
@@ -19,7 +19,6 @@
|
|
| 19 |
},
|
| 20 |
"errors": "replace",
|
| 21 |
"model_max_length": 1024,
|
| 22 |
-
"name_or_path": "openai/whisper-base.en",
|
| 23 |
"pad_token": null,
|
| 24 |
"processor_class": "WhisperProcessor",
|
| 25 |
"return_attention_mask": false,
|
|
|
|
| 19 |
},
|
| 20 |
"errors": "replace",
|
| 21 |
"model_max_length": 1024,
|
|
|
|
| 22 |
"pad_token": null,
|
| 23 |
"processor_class": "WhisperProcessor",
|
| 24 |
"return_attention_mask": false,
|
quantized/openai/whisper-base.en/default/vocab.json
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
quantized/openai/whisper-base.en/speech2seq-lm-with-past/config.json
CHANGED
|
@@ -2,6 +2,7 @@
|
|
| 2 |
"_name_or_path": "openai/whisper-base.en",
|
| 3 |
"activation_dropout": 0.0,
|
| 4 |
"activation_function": "gelu",
|
|
|
|
| 5 |
"architectures": [
|
| 6 |
"WhisperForConditionalGeneration"
|
| 7 |
],
|
|
@@ -11,6 +12,7 @@
|
|
| 11 |
50256
|
| 12 |
],
|
| 13 |
"bos_token_id": 50257,
|
|
|
|
| 14 |
"d_model": 512,
|
| 15 |
"decoder_attention_heads": 8,
|
| 16 |
"decoder_ffn_dim": 2048,
|
|
@@ -31,6 +33,12 @@
|
|
| 31 |
],
|
| 32 |
"init_std": 0.02,
|
| 33 |
"is_encoder_decoder": true,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 34 |
"max_length": 448,
|
| 35 |
"max_source_positions": 1500,
|
| 36 |
"max_target_positions": 448,
|
|
@@ -129,7 +137,8 @@
|
|
| 129 |
50360,
|
| 130 |
50361
|
| 131 |
],
|
| 132 |
-
"transformers_version": "4.
|
| 133 |
"use_cache": true,
|
|
|
|
| 134 |
"vocab_size": 51864
|
| 135 |
}
|
|
|
|
| 2 |
"_name_or_path": "openai/whisper-base.en",
|
| 3 |
"activation_dropout": 0.0,
|
| 4 |
"activation_function": "gelu",
|
| 5 |
+
"apply_spec_augment": false,
|
| 6 |
"architectures": [
|
| 7 |
"WhisperForConditionalGeneration"
|
| 8 |
],
|
|
|
|
| 12 |
50256
|
| 13 |
],
|
| 14 |
"bos_token_id": 50257,
|
| 15 |
+
"classifier_proj_size": 256,
|
| 16 |
"d_model": 512,
|
| 17 |
"decoder_attention_heads": 8,
|
| 18 |
"decoder_ffn_dim": 2048,
|
|
|
|
| 33 |
],
|
| 34 |
"init_std": 0.02,
|
| 35 |
"is_encoder_decoder": true,
|
| 36 |
+
"mask_feature_length": 10,
|
| 37 |
+
"mask_feature_min_masks": 0,
|
| 38 |
+
"mask_feature_prob": 0.0,
|
| 39 |
+
"mask_time_length": 10,
|
| 40 |
+
"mask_time_min_masks": 2,
|
| 41 |
+
"mask_time_prob": 0.05,
|
| 42 |
"max_length": 448,
|
| 43 |
"max_source_positions": 1500,
|
| 44 |
"max_target_positions": 448,
|
|
|
|
| 137 |
50360,
|
| 138 |
50361
|
| 139 |
],
|
| 140 |
+
"transformers_version": "4.27.2",
|
| 141 |
"use_cache": true,
|
| 142 |
+
"use_weighted_layer_sum": false,
|
| 143 |
"vocab_size": 51864
|
| 144 |
}
|
quantized/openai/whisper-base.en/speech2seq-lm-with-past/decoder_model.onnx
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cdbb51eee5ded5368f2892aae40f332440c73c28f805b0f814d6bede9b89f597
|
| 3 |
+
size 80281417
|
quantized/openai/whisper-base.en/speech2seq-lm-with-past/decoder_model_merged.onnx
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1dc1286247e416f25c6d7569e97369ced423c7e1253c9cfcbf20631a267a91ec
|
| 3 |
+
size 80477622
|
quantized/openai/whisper-base.en/speech2seq-lm-with-past/decoder_with_past_model.onnx
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:19c03bc1a84dc5cbc36a0c37b035e08775c72eae4f9b39828c2d5e653fa389c2
|
| 3 |
+
size 77026648
|
quantized/openai/whisper-base.en/speech2seq-lm-with-past/encoder_model.onnx
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2e5c7694b53a299a30beb6c6b9b4934f814cf3382bec0957b612ee0934b78858
|
| 3 |
+
size 23321703
|
quantized/openai/whisper-base.en/speech2seq-lm-with-past/merges.txt
CHANGED
|
@@ -1,4 +1,4 @@
|
|
| 1 |
-
#version: 0.2
|
| 2 |
Ġ t
|
| 3 |
Ġ a
|
| 4 |
h e
|
|
|
|
| 1 |
+
#version: 0.2 - Trained by `huggingface/tokenizers`
|
| 2 |
Ġ t
|
| 3 |
Ġ a
|
| 4 |
h e
|
quantized/openai/whisper-base.en/speech2seq-lm-with-past/tokenizer.json
CHANGED
|
@@ -5,974 +5,973 @@
|
|
| 5 |
"added_tokens": [
|
| 6 |
{
|
| 7 |
"id": 50256,
|
|
|
|
| 8 |
"content": "<|endoftext|>",
|
| 9 |
"single_word": false,
|
| 10 |
"lstrip": false,
|
| 11 |
"rstrip": false,
|
| 12 |
-
"normalized": false
|
| 13 |
-
"special": true
|
| 14 |
},
|
| 15 |
{
|
| 16 |
"id": 50257,
|
|
|
|
| 17 |
"content": "<|startoftranscript|>",
|
| 18 |
"single_word": false,
|
| 19 |
"lstrip": false,
|
| 20 |
"rstrip": false,
|
| 21 |
-
"normalized": false
|
| 22 |
-
"special": true
|
| 23 |
},
|
| 24 |
{
|
| 25 |
"id": 50258,
|
|
|
|
| 26 |
"content": "<|en|>",
|
| 27 |
"single_word": false,
|
| 28 |
"lstrip": false,
|
| 29 |
"rstrip": false,
|
| 30 |
-
"normalized": false
|
| 31 |
-
"special": true
|
| 32 |
},
|
| 33 |
{
|
| 34 |
"id": 50259,
|
|
|
|
| 35 |
"content": "<|zh|>",
|
| 36 |
"single_word": false,
|
| 37 |
"lstrip": false,
|
| 38 |
"rstrip": false,
|
| 39 |
-
"normalized": false
|
| 40 |
-
"special": true
|
| 41 |
},
|
| 42 |
{
|
| 43 |
"id": 50260,
|
|
|
|
| 44 |
"content": "<|de|>",
|
| 45 |
"single_word": false,
|
| 46 |
"lstrip": false,
|
| 47 |
"rstrip": false,
|
| 48 |
-
"normalized": false
|
| 49 |
-
"special": true
|
| 50 |
},
|
| 51 |
{
|
| 52 |
"id": 50261,
|
|
|
|
| 53 |
"content": "<|es|>",
|
| 54 |
"single_word": false,
|
| 55 |
"lstrip": false,
|
| 56 |
"rstrip": false,
|
| 57 |
-
"normalized": false
|
| 58 |
-
"special": true
|
| 59 |
},
|
| 60 |
{
|
| 61 |
"id": 50262,
|
|
|
|
| 62 |
"content": "<|ru|>",
|
| 63 |
"single_word": false,
|
| 64 |
"lstrip": false,
|
| 65 |
"rstrip": false,
|
| 66 |
-
"normalized": false
|
| 67 |
-
"special": true
|
| 68 |
},
|
| 69 |
{
|
| 70 |
"id": 50263,
|
|
|
|
| 71 |
"content": "<|ko|>",
|
| 72 |
"single_word": false,
|
| 73 |
"lstrip": false,
|
| 74 |
"rstrip": false,
|
| 75 |
-
"normalized": false
|
| 76 |
-
"special": true
|
| 77 |
},
|
| 78 |
{
|
| 79 |
"id": 50264,
|
|
|
|
| 80 |
"content": "<|fr|>",
|
| 81 |
"single_word": false,
|
| 82 |
"lstrip": false,
|
| 83 |
"rstrip": false,
|
| 84 |
-
"normalized": false
|
| 85 |
-
"special": true
|
| 86 |
},
|
| 87 |
{
|
| 88 |
"id": 50265,
|
|
|
|
| 89 |
"content": "<|ja|>",
|
| 90 |
"single_word": false,
|
| 91 |
"lstrip": false,
|
| 92 |
"rstrip": false,
|
| 93 |
-
"normalized": false
|
| 94 |
-
"special": true
|
| 95 |
},
|
| 96 |
{
|
| 97 |
"id": 50266,
|
|
|
|
| 98 |
"content": "<|pt|>",
|
| 99 |
"single_word": false,
|
| 100 |
"lstrip": false,
|
| 101 |
"rstrip": false,
|
| 102 |
-
"normalized": false
|
| 103 |
-
"special": true
|
| 104 |
},
|
| 105 |
{
|
| 106 |
"id": 50267,
|
|
|
|
| 107 |
"content": "<|tr|>",
|
| 108 |
"single_word": false,
|
| 109 |
"lstrip": false,
|
| 110 |
"rstrip": false,
|
| 111 |
-
"normalized": false
|
| 112 |
-
"special": true
|
| 113 |
},
|
| 114 |
{
|
| 115 |
"id": 50268,
|
|
|
|
| 116 |
"content": "<|pl|>",
|
| 117 |
"single_word": false,
|
| 118 |
"lstrip": false,
|
| 119 |
"rstrip": false,
|
| 120 |
-
"normalized": false
|
| 121 |
-
"special": true
|
| 122 |
},
|
| 123 |
{
|
| 124 |
"id": 50269,
|
|
|
|
| 125 |
"content": "<|ca|>",
|
| 126 |
"single_word": false,
|
| 127 |
"lstrip": false,
|
| 128 |
"rstrip": false,
|
| 129 |
-
"normalized": false
|
| 130 |
-
"special": true
|
| 131 |
},
|
| 132 |
{
|
| 133 |
"id": 50270,
|
|
|
|
| 134 |
"content": "<|nl|>",
|
| 135 |
"single_word": false,
|
| 136 |
"lstrip": false,
|
| 137 |
"rstrip": false,
|
| 138 |
-
"normalized": false
|
| 139 |
-
"special": true
|
| 140 |
},
|
| 141 |
{
|
| 142 |
"id": 50271,
|
|
|
|
| 143 |
"content": "<|ar|>",
|
| 144 |
"single_word": false,
|
| 145 |
"lstrip": false,
|
| 146 |
"rstrip": false,
|
| 147 |
-
"normalized": false
|
| 148 |
-
"special": true
|
| 149 |
},
|
| 150 |
{
|
| 151 |
"id": 50272,
|
|
|
|
| 152 |
"content": "<|sv|>",
|
| 153 |
"single_word": false,
|
| 154 |
"lstrip": false,
|
| 155 |
"rstrip": false,
|
| 156 |
-
"normalized": false
|
| 157 |
-
"special": true
|
| 158 |
},
|
| 159 |
{
|
| 160 |
"id": 50273,
|
|
|
|
| 161 |
"content": "<|it|>",
|
| 162 |
"single_word": false,
|
| 163 |
"lstrip": false,
|
| 164 |
"rstrip": false,
|
| 165 |
-
"normalized": false
|
| 166 |
-
"special": true
|
| 167 |
},
|
| 168 |
{
|
| 169 |
"id": 50274,
|
|
|
|
| 170 |
"content": "<|id|>",
|
| 171 |
"single_word": false,
|
| 172 |
"lstrip": false,
|
| 173 |
"rstrip": false,
|
| 174 |
-
"normalized": false
|
| 175 |
-
"special": true
|
| 176 |
},
|
| 177 |
{
|
| 178 |
"id": 50275,
|
|
|
|
| 179 |
"content": "<|hi|>",
|
| 180 |
"single_word": false,
|
| 181 |
"lstrip": false,
|
| 182 |
"rstrip": false,
|
| 183 |
-
"normalized": false
|
| 184 |
-
"special": true
|
| 185 |
},
|
| 186 |
{
|
| 187 |
"id": 50276,
|
|
|
|
| 188 |
"content": "<|fi|>",
|
| 189 |
"single_word": false,
|
| 190 |
"lstrip": false,
|
| 191 |
"rstrip": false,
|
| 192 |
-
"normalized": false
|
| 193 |
-
"special": true
|
| 194 |
},
|
| 195 |
{
|
| 196 |
"id": 50277,
|
|
|
|
| 197 |
"content": "<|vi|>",
|
| 198 |
"single_word": false,
|
| 199 |
"lstrip": false,
|
| 200 |
"rstrip": false,
|
| 201 |
-
"normalized": false
|
| 202 |
-
"special": true
|
| 203 |
},
|
| 204 |
{
|
| 205 |
"id": 50278,
|
|
|
|
| 206 |
"content": "<|iw|>",
|
| 207 |
"single_word": false,
|
| 208 |
"lstrip": false,
|
| 209 |
"rstrip": false,
|
| 210 |
-
"normalized": false
|
| 211 |
-
"special": true
|
| 212 |
},
|
| 213 |
{
|
| 214 |
"id": 50279,
|
|
|
|
| 215 |
"content": "<|uk|>",
|
| 216 |
"single_word": false,
|
| 217 |
"lstrip": false,
|
| 218 |
"rstrip": false,
|
| 219 |
-
"normalized": false
|
| 220 |
-
"special": true
|
| 221 |
},
|
| 222 |
{
|
| 223 |
"id": 50280,
|
|
|
|
| 224 |
"content": "<|el|>",
|
| 225 |
"single_word": false,
|
| 226 |
"lstrip": false,
|
| 227 |
"rstrip": false,
|
| 228 |
-
"normalized": false
|
| 229 |
-
"special": true
|
| 230 |
},
|
| 231 |
{
|
| 232 |
"id": 50281,
|
|
|
|
| 233 |
"content": "<|ms|>",
|
| 234 |
"single_word": false,
|
| 235 |
"lstrip": false,
|
| 236 |
"rstrip": false,
|
| 237 |
-
"normalized": false
|
| 238 |
-
"special": true
|
| 239 |
},
|
| 240 |
{
|
| 241 |
"id": 50282,
|
|
|
|
| 242 |
"content": "<|cs|>",
|
| 243 |
"single_word": false,
|
| 244 |
"lstrip": false,
|
| 245 |
"rstrip": false,
|
| 246 |
-
"normalized": false
|
| 247 |
-
"special": true
|
| 248 |
},
|
| 249 |
{
|
| 250 |
"id": 50283,
|
|
|
|
| 251 |
"content": "<|ro|>",
|
| 252 |
"single_word": false,
|
| 253 |
"lstrip": false,
|
| 254 |
"rstrip": false,
|
| 255 |
-
"normalized": false
|
| 256 |
-
"special": true
|
| 257 |
},
|
| 258 |
{
|
| 259 |
"id": 50284,
|
|
|
|
| 260 |
"content": "<|da|>",
|
| 261 |
"single_word": false,
|
| 262 |
"lstrip": false,
|
| 263 |
"rstrip": false,
|
| 264 |
-
"normalized": false
|
| 265 |
-
"special": true
|
| 266 |
},
|
| 267 |
{
|
| 268 |
"id": 50285,
|
|
|
|
| 269 |
"content": "<|hu|>",
|
| 270 |
"single_word": false,
|
| 271 |
"lstrip": false,
|
| 272 |
"rstrip": false,
|
| 273 |
-
"normalized": false
|
| 274 |
-
"special": true
|
| 275 |
},
|
| 276 |
{
|
| 277 |
"id": 50286,
|
|
|
|
| 278 |
"content": "<|ta|>",
|
| 279 |
"single_word": false,
|
| 280 |
"lstrip": false,
|
| 281 |
"rstrip": false,
|
| 282 |
-
"normalized": false
|
| 283 |
-
"special": true
|
| 284 |
},
|
| 285 |
{
|
| 286 |
"id": 50287,
|
|
|
|
| 287 |
"content": "<|no|>",
|
| 288 |
"single_word": false,
|
| 289 |
"lstrip": false,
|
| 290 |
"rstrip": false,
|
| 291 |
-
"normalized": false
|
| 292 |
-
"special": true
|
| 293 |
},
|
| 294 |
{
|
| 295 |
"id": 50288,
|
|
|
|
| 296 |
"content": "<|th|>",
|
| 297 |
"single_word": false,
|
| 298 |
"lstrip": false,
|
| 299 |
"rstrip": false,
|
| 300 |
-
"normalized": false
|
| 301 |
-
"special": true
|
| 302 |
},
|
| 303 |
{
|
| 304 |
"id": 50289,
|
|
|
|
| 305 |
"content": "<|ur|>",
|
| 306 |
"single_word": false,
|
| 307 |
"lstrip": false,
|
| 308 |
"rstrip": false,
|
| 309 |
-
"normalized": false
|
| 310 |
-
"special": true
|
| 311 |
},
|
| 312 |
{
|
| 313 |
"id": 50290,
|
|
|
|
| 314 |
"content": "<|hr|>",
|
| 315 |
"single_word": false,
|
| 316 |
"lstrip": false,
|
| 317 |
"rstrip": false,
|
| 318 |
-
"normalized": false
|
| 319 |
-
"special": true
|
| 320 |
},
|
| 321 |
{
|
| 322 |
"id": 50291,
|
|
|
|
| 323 |
"content": "<|bg|>",
|
| 324 |
"single_word": false,
|
| 325 |
"lstrip": false,
|
| 326 |
"rstrip": false,
|
| 327 |
-
"normalized": false
|
| 328 |
-
"special": true
|
| 329 |
},
|
| 330 |
{
|
| 331 |
"id": 50292,
|
|
|
|
| 332 |
"content": "<|lt|>",
|
| 333 |
"single_word": false,
|
| 334 |
"lstrip": false,
|
| 335 |
"rstrip": false,
|
| 336 |
-
"normalized": false
|
| 337 |
-
"special": true
|
| 338 |
},
|
| 339 |
{
|
| 340 |
"id": 50293,
|
|
|
|
| 341 |
"content": "<|la|>",
|
| 342 |
"single_word": false,
|
| 343 |
"lstrip": false,
|
| 344 |
"rstrip": false,
|
| 345 |
-
"normalized": false
|
| 346 |
-
"special": true
|
| 347 |
},
|
| 348 |
{
|
| 349 |
"id": 50294,
|
|
|
|
| 350 |
"content": "<|mi|>",
|
| 351 |
"single_word": false,
|
| 352 |
"lstrip": false,
|
| 353 |
"rstrip": false,
|
| 354 |
-
"normalized": false
|
| 355 |
-
"special": true
|
| 356 |
},
|
| 357 |
{
|
| 358 |
"id": 50295,
|
|
|
|
| 359 |
"content": "<|ml|>",
|
| 360 |
"single_word": false,
|
| 361 |
"lstrip": false,
|
| 362 |
"rstrip": false,
|
| 363 |
-
"normalized": false
|
| 364 |
-
"special": true
|
| 365 |
},
|
| 366 |
{
|
| 367 |
"id": 50296,
|
|
|
|
| 368 |
"content": "<|cy|>",
|
| 369 |
"single_word": false,
|
| 370 |
"lstrip": false,
|
| 371 |
"rstrip": false,
|
| 372 |
-
"normalized": false
|
| 373 |
-
"special": true
|
| 374 |
},
|
| 375 |
{
|
| 376 |
"id": 50297,
|
|
|
|
| 377 |
"content": "<|sk|>",
|
| 378 |
"single_word": false,
|
| 379 |
"lstrip": false,
|
| 380 |
"rstrip": false,
|
| 381 |
-
"normalized": false
|
| 382 |
-
"special": true
|
| 383 |
},
|
| 384 |
{
|
| 385 |
"id": 50298,
|
|
|
|
| 386 |
"content": "<|te|>",
|
| 387 |
"single_word": false,
|
| 388 |
"lstrip": false,
|
| 389 |
"rstrip": false,
|
| 390 |
-
"normalized": false
|
| 391 |
-
"special": true
|
| 392 |
},
|
| 393 |
{
|
| 394 |
"id": 50299,
|
|
|
|
| 395 |
"content": "<|fa|>",
|
| 396 |
"single_word": false,
|
| 397 |
"lstrip": false,
|
| 398 |
"rstrip": false,
|
| 399 |
-
"normalized": false
|
| 400 |
-
"special": true
|
| 401 |
},
|
| 402 |
{
|
| 403 |
"id": 50300,
|
|
|
|
| 404 |
"content": "<|lv|>",
|
| 405 |
"single_word": false,
|
| 406 |
"lstrip": false,
|
| 407 |
"rstrip": false,
|
| 408 |
-
"normalized": false
|
| 409 |
-
"special": true
|
| 410 |
},
|
| 411 |
{
|
| 412 |
"id": 50301,
|
|
|
|
| 413 |
"content": "<|bn|>",
|
| 414 |
"single_word": false,
|
| 415 |
"lstrip": false,
|
| 416 |
"rstrip": false,
|
| 417 |
-
"normalized": false
|
| 418 |
-
"special": true
|
| 419 |
},
|
| 420 |
{
|
| 421 |
"id": 50302,
|
|
|
|
| 422 |
"content": "<|sr|>",
|
| 423 |
"single_word": false,
|
| 424 |
"lstrip": false,
|
| 425 |
"rstrip": false,
|
| 426 |
-
"normalized": false
|
| 427 |
-
"special": true
|
| 428 |
},
|
| 429 |
{
|
| 430 |
"id": 50303,
|
|
|
|
| 431 |
"content": "<|az|>",
|
| 432 |
"single_word": false,
|
| 433 |
"lstrip": false,
|
| 434 |
"rstrip": false,
|
| 435 |
-
"normalized": false
|
| 436 |
-
"special": true
|
| 437 |
},
|
| 438 |
{
|
| 439 |
"id": 50304,
|
|
|
|
| 440 |
"content": "<|sl|>",
|
| 441 |
"single_word": false,
|
| 442 |
"lstrip": false,
|
| 443 |
"rstrip": false,
|
| 444 |
-
"normalized": false
|
| 445 |
-
"special": true
|
| 446 |
},
|
| 447 |
{
|
| 448 |
"id": 50305,
|
|
|
|
| 449 |
"content": "<|kn|>",
|
| 450 |
"single_word": false,
|
| 451 |
"lstrip": false,
|
| 452 |
"rstrip": false,
|
| 453 |
-
"normalized": false
|
| 454 |
-
"special": true
|
| 455 |
},
|
| 456 |
{
|
| 457 |
"id": 50306,
|
|
|
|
| 458 |
"content": "<|et|>",
|
| 459 |
"single_word": false,
|
| 460 |
"lstrip": false,
|
| 461 |
"rstrip": false,
|
| 462 |
-
"normalized": false
|
| 463 |
-
"special": true
|
| 464 |
},
|
| 465 |
{
|
| 466 |
"id": 50307,
|
|
|
|
| 467 |
"content": "<|mk|>",
|
| 468 |
"single_word": false,
|
| 469 |
"lstrip": false,
|
| 470 |
"rstrip": false,
|
| 471 |
-
"normalized": false
|
| 472 |
-
"special": true
|
| 473 |
},
|
| 474 |
{
|
| 475 |
"id": 50308,
|
|
|
|
| 476 |
"content": "<|br|>",
|
| 477 |
"single_word": false,
|
| 478 |
"lstrip": false,
|
| 479 |
"rstrip": false,
|
| 480 |
-
"normalized": false
|
| 481 |
-
"special": true
|
| 482 |
},
|
| 483 |
{
|
| 484 |
"id": 50309,
|
|
|
|
| 485 |
"content": "<|eu|>",
|
| 486 |
"single_word": false,
|
| 487 |
"lstrip": false,
|
| 488 |
"rstrip": false,
|
| 489 |
-
"normalized": false
|
| 490 |
-
"special": true
|
| 491 |
},
|
| 492 |
{
|
| 493 |
"id": 50310,
|
|
|
|
| 494 |
"content": "<|is|>",
|
| 495 |
"single_word": false,
|
| 496 |
"lstrip": false,
|
| 497 |
"rstrip": false,
|
| 498 |
-
"normalized": false
|
| 499 |
-
"special": true
|
| 500 |
},
|
| 501 |
{
|
| 502 |
"id": 50311,
|
|
|
|
| 503 |
"content": "<|hy|>",
|
| 504 |
"single_word": false,
|
| 505 |
"lstrip": false,
|
| 506 |
"rstrip": false,
|
| 507 |
-
"normalized": false
|
| 508 |
-
"special": true
|
| 509 |
},
|
| 510 |
{
|
| 511 |
"id": 50312,
|
|
|
|
| 512 |
"content": "<|ne|>",
|
| 513 |
"single_word": false,
|
| 514 |
"lstrip": false,
|
| 515 |
"rstrip": false,
|
| 516 |
-
"normalized": false
|
| 517 |
-
"special": true
|
| 518 |
},
|
| 519 |
{
|
| 520 |
"id": 50313,
|
|
|
|
| 521 |
"content": "<|mn|>",
|
| 522 |
"single_word": false,
|
| 523 |
"lstrip": false,
|
| 524 |
"rstrip": false,
|
| 525 |
-
"normalized": false
|
| 526 |
-
"special": true
|
| 527 |
},
|
| 528 |
{
|
| 529 |
"id": 50314,
|
|
|
|
| 530 |
"content": "<|bs|>",
|
| 531 |
"single_word": false,
|
| 532 |
"lstrip": false,
|
| 533 |
"rstrip": false,
|
| 534 |
-
"normalized": false
|
| 535 |
-
"special": true
|
| 536 |
},
|
| 537 |
{
|
| 538 |
"id": 50315,
|
|
|
|
| 539 |
"content": "<|kk|>",
|
| 540 |
"single_word": false,
|
| 541 |
"lstrip": false,
|
| 542 |
"rstrip": false,
|
| 543 |
-
"normalized": false
|
| 544 |
-
"special": true
|
| 545 |
},
|
| 546 |
{
|
| 547 |
"id": 50316,
|
|
|
|
| 548 |
"content": "<|sq|>",
|
| 549 |
"single_word": false,
|
| 550 |
"lstrip": false,
|
| 551 |
"rstrip": false,
|
| 552 |
-
"normalized": false
|
| 553 |
-
"special": true
|
| 554 |
},
|
| 555 |
{
|
| 556 |
"id": 50317,
|
|
|
|
| 557 |
"content": "<|sw|>",
|
| 558 |
"single_word": false,
|
| 559 |
"lstrip": false,
|
| 560 |
"rstrip": false,
|
| 561 |
-
"normalized": false
|
| 562 |
-
"special": true
|
| 563 |
},
|
| 564 |
{
|
| 565 |
"id": 50318,
|
|
|
|
| 566 |
"content": "<|gl|>",
|
| 567 |
"single_word": false,
|
| 568 |
"lstrip": false,
|
| 569 |
"rstrip": false,
|
| 570 |
-
"normalized": false
|
| 571 |
-
"special": true
|
| 572 |
},
|
| 573 |
{
|
| 574 |
"id": 50319,
|
|
|
|
| 575 |
"content": "<|mr|>",
|
| 576 |
"single_word": false,
|
| 577 |
"lstrip": false,
|
| 578 |
"rstrip": false,
|
| 579 |
-
"normalized": false
|
| 580 |
-
"special": true
|
| 581 |
},
|
| 582 |
{
|
| 583 |
"id": 50320,
|
|
|
|
| 584 |
"content": "<|pa|>",
|
| 585 |
"single_word": false,
|
| 586 |
"lstrip": false,
|
| 587 |
"rstrip": false,
|
| 588 |
-
"normalized": false
|
| 589 |
-
"special": true
|
| 590 |
},
|
| 591 |
{
|
| 592 |
"id": 50321,
|
|
|
|
| 593 |
"content": "<|si|>",
|
| 594 |
"single_word": false,
|
| 595 |
"lstrip": false,
|
| 596 |
"rstrip": false,
|
| 597 |
-
"normalized": false
|
| 598 |
-
"special": true
|
| 599 |
},
|
| 600 |
{
|
| 601 |
"id": 50322,
|
|
|
|
| 602 |
"content": "<|km|>",
|
| 603 |
"single_word": false,
|
| 604 |
"lstrip": false,
|
| 605 |
"rstrip": false,
|
| 606 |
-
"normalized": false
|
| 607 |
-
"special": true
|
| 608 |
},
|
| 609 |
{
|
| 610 |
"id": 50323,
|
|
|
|
| 611 |
"content": "<|sn|>",
|
| 612 |
"single_word": false,
|
| 613 |
"lstrip": false,
|
| 614 |
"rstrip": false,
|
| 615 |
-
"normalized": false
|
| 616 |
-
"special": true
|
| 617 |
},
|
| 618 |
{
|
| 619 |
"id": 50324,
|
|
|
|
| 620 |
"content": "<|yo|>",
|
| 621 |
"single_word": false,
|
| 622 |
"lstrip": false,
|
| 623 |
"rstrip": false,
|
| 624 |
-
"normalized": false
|
| 625 |
-
"special": true
|
| 626 |
},
|
| 627 |
{
|
| 628 |
"id": 50325,
|
|
|
|
| 629 |
"content": "<|so|>",
|
| 630 |
"single_word": false,
|
| 631 |
"lstrip": false,
|
| 632 |
"rstrip": false,
|
| 633 |
-
"normalized": false
|
| 634 |
-
"special": true
|
| 635 |
},
|
| 636 |
{
|
| 637 |
"id": 50326,
|
|
|
|
| 638 |
"content": "<|af|>",
|
| 639 |
"single_word": false,
|
| 640 |
"lstrip": false,
|
| 641 |
"rstrip": false,
|
| 642 |
-
"normalized": false
|
| 643 |
-
"special": true
|
| 644 |
},
|
| 645 |
{
|
| 646 |
"id": 50327,
|
|
|
|
| 647 |
"content": "<|oc|>",
|
| 648 |
"single_word": false,
|
| 649 |
"lstrip": false,
|
| 650 |
"rstrip": false,
|
| 651 |
-
"normalized": false
|
| 652 |
-
"special": true
|
| 653 |
},
|
| 654 |
{
|
| 655 |
"id": 50328,
|
|
|
|
| 656 |
"content": "<|ka|>",
|
| 657 |
"single_word": false,
|
| 658 |
"lstrip": false,
|
| 659 |
"rstrip": false,
|
| 660 |
-
"normalized": false
|
| 661 |
-
"special": true
|
| 662 |
},
|
| 663 |
{
|
| 664 |
"id": 50329,
|
|
|
|
| 665 |
"content": "<|be|>",
|
| 666 |
"single_word": false,
|
| 667 |
"lstrip": false,
|
| 668 |
"rstrip": false,
|
| 669 |
-
"normalized": false
|
| 670 |
-
"special": true
|
| 671 |
},
|
| 672 |
{
|
| 673 |
"id": 50330,
|
|
|
|
| 674 |
"content": "<|tg|>",
|
| 675 |
"single_word": false,
|
| 676 |
"lstrip": false,
|
| 677 |
"rstrip": false,
|
| 678 |
-
"normalized": false
|
| 679 |
-
"special": true
|
| 680 |
},
|
| 681 |
{
|
| 682 |
"id": 50331,
|
|
|
|
| 683 |
"content": "<|sd|>",
|
| 684 |
"single_word": false,
|
| 685 |
"lstrip": false,
|
| 686 |
"rstrip": false,
|
| 687 |
-
"normalized": false
|
| 688 |
-
"special": true
|
| 689 |
},
|
| 690 |
{
|
| 691 |
"id": 50332,
|
|
|
|
| 692 |
"content": "<|gu|>",
|
| 693 |
"single_word": false,
|
| 694 |
"lstrip": false,
|
| 695 |
"rstrip": false,
|
| 696 |
-
"normalized": false
|
| 697 |
-
"special": true
|
| 698 |
},
|
| 699 |
{
|
| 700 |
"id": 50333,
|
|
|
|
| 701 |
"content": "<|am|>",
|
| 702 |
"single_word": false,
|
| 703 |
"lstrip": false,
|
| 704 |
"rstrip": false,
|
| 705 |
-
"normalized": false
|
| 706 |
-
"special": true
|
| 707 |
},
|
| 708 |
{
|
| 709 |
"id": 50334,
|
|
|
|
| 710 |
"content": "<|yi|>",
|
| 711 |
"single_word": false,
|
| 712 |
"lstrip": false,
|
| 713 |
"rstrip": false,
|
| 714 |
-
"normalized": false
|
| 715 |
-
"special": true
|
| 716 |
},
|
| 717 |
{
|
| 718 |
"id": 50335,
|
|
|
|
| 719 |
"content": "<|lo|>",
|
| 720 |
"single_word": false,
|
| 721 |
"lstrip": false,
|
| 722 |
"rstrip": false,
|
| 723 |
-
"normalized": false
|
| 724 |
-
"special": true
|
| 725 |
},
|
| 726 |
{
|
| 727 |
"id": 50336,
|
|
|
|
| 728 |
"content": "<|uz|>",
|
| 729 |
"single_word": false,
|
| 730 |
"lstrip": false,
|
| 731 |
"rstrip": false,
|
| 732 |
-
"normalized": false
|
| 733 |
-
"special": true
|
| 734 |
},
|
| 735 |
{
|
| 736 |
"id": 50337,
|
|
|
|
| 737 |
"content": "<|fo|>",
|
| 738 |
"single_word": false,
|
| 739 |
"lstrip": false,
|
| 740 |
"rstrip": false,
|
| 741 |
-
"normalized": false
|
| 742 |
-
"special": true
|
| 743 |
},
|
| 744 |
{
|
| 745 |
"id": 50338,
|
|
|
|
| 746 |
"content": "<|ht|>",
|
| 747 |
"single_word": false,
|
| 748 |
"lstrip": false,
|
| 749 |
"rstrip": false,
|
| 750 |
-
"normalized": false
|
| 751 |
-
"special": true
|
| 752 |
},
|
| 753 |
{
|
| 754 |
"id": 50339,
|
|
|
|
| 755 |
"content": "<|ps|>",
|
| 756 |
"single_word": false,
|
| 757 |
"lstrip": false,
|
| 758 |
"rstrip": false,
|
| 759 |
-
"normalized": false
|
| 760 |
-
"special": true
|
| 761 |
},
|
| 762 |
{
|
| 763 |
"id": 50340,
|
|
|
|
| 764 |
"content": "<|tk|>",
|
| 765 |
"single_word": false,
|
| 766 |
"lstrip": false,
|
| 767 |
"rstrip": false,
|
| 768 |
-
"normalized": false
|
| 769 |
-
"special": true
|
| 770 |
},
|
| 771 |
{
|
| 772 |
"id": 50341,
|
|
|
|
| 773 |
"content": "<|nn|>",
|
| 774 |
"single_word": false,
|
| 775 |
"lstrip": false,
|
| 776 |
"rstrip": false,
|
| 777 |
-
"normalized": false
|
| 778 |
-
"special": true
|
| 779 |
},
|
| 780 |
{
|
| 781 |
"id": 50342,
|
|
|
|
| 782 |
"content": "<|mt|>",
|
| 783 |
"single_word": false,
|
| 784 |
"lstrip": false,
|
| 785 |
"rstrip": false,
|
| 786 |
-
"normalized": false
|
| 787 |
-
"special": true
|
| 788 |
},
|
| 789 |
{
|
| 790 |
"id": 50343,
|
|
|
|
| 791 |
"content": "<|sa|>",
|
| 792 |
"single_word": false,
|
| 793 |
"lstrip": false,
|
| 794 |
"rstrip": false,
|
| 795 |
-
"normalized": false
|
| 796 |
-
"special": true
|
| 797 |
},
|
| 798 |
{
|
| 799 |
"id": 50344,
|
|
|
|
| 800 |
"content": "<|lb|>",
|
| 801 |
"single_word": false,
|
| 802 |
"lstrip": false,
|
| 803 |
"rstrip": false,
|
| 804 |
-
"normalized": false
|
| 805 |
-
"special": true
|
| 806 |
},
|
| 807 |
{
|
| 808 |
"id": 50345,
|
|
|
|
| 809 |
"content": "<|my|>",
|
| 810 |
"single_word": false,
|
| 811 |
"lstrip": false,
|
| 812 |
"rstrip": false,
|
| 813 |
-
"normalized": false
|
| 814 |
-
"special": true
|
| 815 |
},
|
| 816 |
{
|
| 817 |
"id": 50346,
|
|
|
|
| 818 |
"content": "<|bo|>",
|
| 819 |
"single_word": false,
|
| 820 |
"lstrip": false,
|
| 821 |
"rstrip": false,
|
| 822 |
-
"normalized": false
|
| 823 |
-
"special": true
|
| 824 |
},
|
| 825 |
{
|
| 826 |
"id": 50347,
|
|
|
|
| 827 |
"content": "<|tl|>",
|
| 828 |
"single_word": false,
|
| 829 |
"lstrip": false,
|
| 830 |
"rstrip": false,
|
| 831 |
-
"normalized": false
|
| 832 |
-
"special": true
|
| 833 |
},
|
| 834 |
{
|
| 835 |
"id": 50348,
|
|
|
|
| 836 |
"content": "<|mg|>",
|
| 837 |
"single_word": false,
|
| 838 |
"lstrip": false,
|
| 839 |
"rstrip": false,
|
| 840 |
-
"normalized": false
|
| 841 |
-
"special": true
|
| 842 |
},
|
| 843 |
{
|
| 844 |
"id": 50349,
|
|
|
|
| 845 |
"content": "<|as|>",
|
| 846 |
"single_word": false,
|
| 847 |
"lstrip": false,
|
| 848 |
"rstrip": false,
|
| 849 |
-
"normalized": false
|
| 850 |
-
"special": true
|
| 851 |
},
|
| 852 |
{
|
| 853 |
"id": 50350,
|
|
|
|
| 854 |
"content": "<|tt|>",
|
| 855 |
"single_word": false,
|
| 856 |
"lstrip": false,
|
| 857 |
"rstrip": false,
|
| 858 |
-
"normalized": false
|
| 859 |
-
"special": true
|
| 860 |
},
|
| 861 |
{
|
| 862 |
"id": 50351,
|
|
|
|
| 863 |
"content": "<|haw|>",
|
| 864 |
"single_word": false,
|
| 865 |
"lstrip": false,
|
| 866 |
"rstrip": false,
|
| 867 |
-
"normalized": false
|
| 868 |
-
"special": true
|
| 869 |
},
|
| 870 |
{
|
| 871 |
"id": 50352,
|
|
|
|
| 872 |
"content": "<|ln|>",
|
| 873 |
"single_word": false,
|
| 874 |
"lstrip": false,
|
| 875 |
"rstrip": false,
|
| 876 |
-
"normalized": false
|
| 877 |
-
"special": true
|
| 878 |
},
|
| 879 |
{
|
| 880 |
"id": 50353,
|
|
|
|
| 881 |
"content": "<|ha|>",
|
| 882 |
"single_word": false,
|
| 883 |
"lstrip": false,
|
| 884 |
"rstrip": false,
|
| 885 |
-
"normalized": false
|
| 886 |
-
"special": true
|
| 887 |
},
|
| 888 |
{
|
| 889 |
"id": 50354,
|
|
|
|
| 890 |
"content": "<|ba|>",
|
| 891 |
"single_word": false,
|
| 892 |
"lstrip": false,
|
| 893 |
"rstrip": false,
|
| 894 |
-
"normalized": false
|
| 895 |
-
"special": true
|
| 896 |
},
|
| 897 |
{
|
| 898 |
"id": 50355,
|
|
|
|
| 899 |
"content": "<|jw|>",
|
| 900 |
"single_word": false,
|
| 901 |
"lstrip": false,
|
| 902 |
"rstrip": false,
|
| 903 |
-
"normalized": false
|
| 904 |
-
"special": true
|
| 905 |
},
|
| 906 |
{
|
| 907 |
"id": 50356,
|
|
|
|
| 908 |
"content": "<|su|>",
|
| 909 |
"single_word": false,
|
| 910 |
"lstrip": false,
|
| 911 |
"rstrip": false,
|
| 912 |
-
"normalized": false
|
| 913 |
-
"special": true
|
| 914 |
},
|
| 915 |
{
|
| 916 |
"id": 50357,
|
|
|
|
| 917 |
"content": "<|translate|>",
|
| 918 |
"single_word": false,
|
| 919 |
"lstrip": false,
|
| 920 |
"rstrip": false,
|
| 921 |
-
"normalized": false
|
| 922 |
-
"special": true
|
| 923 |
},
|
| 924 |
{
|
| 925 |
"id": 50358,
|
|
|
|
| 926 |
"content": "<|transcribe|>",
|
| 927 |
"single_word": false,
|
| 928 |
"lstrip": false,
|
| 929 |
"rstrip": false,
|
| 930 |
-
"normalized": false
|
| 931 |
-
"special": true
|
| 932 |
},
|
| 933 |
{
|
| 934 |
"id": 50359,
|
|
|
|
| 935 |
"content": "<|startoflm|>",
|
| 936 |
"single_word": false,
|
| 937 |
"lstrip": false,
|
| 938 |
"rstrip": false,
|
| 939 |
-
"normalized": false
|
| 940 |
-
"special": true
|
| 941 |
},
|
| 942 |
{
|
| 943 |
"id": 50360,
|
|
|
|
| 944 |
"content": "<|startofprev|>",
|
| 945 |
"single_word": false,
|
| 946 |
"lstrip": false,
|
| 947 |
"rstrip": false,
|
| 948 |
-
"normalized": false
|
| 949 |
-
"special": true
|
| 950 |
},
|
| 951 |
{
|
| 952 |
"id": 50361,
|
|
|
|
| 953 |
"content": "<|nocaptions|>",
|
| 954 |
"single_word": false,
|
| 955 |
"lstrip": false,
|
| 956 |
"rstrip": false,
|
| 957 |
-
"normalized": false
|
| 958 |
-
"special": true
|
| 959 |
},
|
| 960 |
{
|
| 961 |
"id": 50362,
|
|
|
|
| 962 |
"content": "<|notimestamps|>",
|
| 963 |
"single_word": false,
|
| 964 |
"lstrip": false,
|
| 965 |
"rstrip": false,
|
| 966 |
-
"normalized": false
|
| 967 |
-
"special": true
|
| 968 |
}
|
| 969 |
],
|
| 970 |
"normalizer": null,
|
| 971 |
"pre_tokenizer": {
|
| 972 |
"type": "ByteLevel",
|
| 973 |
"add_prefix_space": false,
|
| 974 |
-
"trim_offsets": true
|
| 975 |
-
"use_regex": true
|
| 976 |
},
|
| 977 |
"post_processor": {
|
| 978 |
"type": "TemplateProcessing",
|
|
@@ -1067,8 +1066,7 @@
|
|
| 1067 |
"decoder": {
|
| 1068 |
"type": "ByteLevel",
|
| 1069 |
"add_prefix_space": true,
|
| 1070 |
-
"trim_offsets": true
|
| 1071 |
-
"use_regex": true
|
| 1072 |
},
|
| 1073 |
"model": {
|
| 1074 |
"type": "BPE",
|
|
|
|
| 5 |
"added_tokens": [
|
| 6 |
{
|
| 7 |
"id": 50256,
|
| 8 |
+
"special": true,
|
| 9 |
"content": "<|endoftext|>",
|
| 10 |
"single_word": false,
|
| 11 |
"lstrip": false,
|
| 12 |
"rstrip": false,
|
| 13 |
+
"normalized": false
|
|
|
|
| 14 |
},
|
| 15 |
{
|
| 16 |
"id": 50257,
|
| 17 |
+
"special": true,
|
| 18 |
"content": "<|startoftranscript|>",
|
| 19 |
"single_word": false,
|
| 20 |
"lstrip": false,
|
| 21 |
"rstrip": false,
|
| 22 |
+
"normalized": false
|
|
|
|
| 23 |
},
|
| 24 |
{
|
| 25 |
"id": 50258,
|
| 26 |
+
"special": true,
|
| 27 |
"content": "<|en|>",
|
| 28 |
"single_word": false,
|
| 29 |
"lstrip": false,
|
| 30 |
"rstrip": false,
|
| 31 |
+
"normalized": false
|
|
|
|
| 32 |
},
|
| 33 |
{
|
| 34 |
"id": 50259,
|
| 35 |
+
"special": true,
|
| 36 |
"content": "<|zh|>",
|
| 37 |
"single_word": false,
|
| 38 |
"lstrip": false,
|
| 39 |
"rstrip": false,
|
| 40 |
+
"normalized": false
|
|
|
|
| 41 |
},
|
| 42 |
{
|
| 43 |
"id": 50260,
|
| 44 |
+
"special": true,
|
| 45 |
"content": "<|de|>",
|
| 46 |
"single_word": false,
|
| 47 |
"lstrip": false,
|
| 48 |
"rstrip": false,
|
| 49 |
+
"normalized": false
|
|
|
|
| 50 |
},
|
| 51 |
{
|
| 52 |
"id": 50261,
|
| 53 |
+
"special": true,
|
| 54 |
"content": "<|es|>",
|
| 55 |
"single_word": false,
|
| 56 |
"lstrip": false,
|
| 57 |
"rstrip": false,
|
| 58 |
+
"normalized": false
|
|
|
|
| 59 |
},
|
| 60 |
{
|
| 61 |
"id": 50262,
|
| 62 |
+
"special": true,
|
| 63 |
"content": "<|ru|>",
|
| 64 |
"single_word": false,
|
| 65 |
"lstrip": false,
|
| 66 |
"rstrip": false,
|
| 67 |
+
"normalized": false
|
|
|
|
| 68 |
},
|
| 69 |
{
|
| 70 |
"id": 50263,
|
| 71 |
+
"special": true,
|
| 72 |
"content": "<|ko|>",
|
| 73 |
"single_word": false,
|
| 74 |
"lstrip": false,
|
| 75 |
"rstrip": false,
|
| 76 |
+
"normalized": false
|
|
|
|
| 77 |
},
|
| 78 |
{
|
| 79 |
"id": 50264,
|
| 80 |
+
"special": true,
|
| 81 |
"content": "<|fr|>",
|
| 82 |
"single_word": false,
|
| 83 |
"lstrip": false,
|
| 84 |
"rstrip": false,
|
| 85 |
+
"normalized": false
|
|
|
|
| 86 |
},
|
| 87 |
{
|
| 88 |
"id": 50265,
|
| 89 |
+
"special": true,
|
| 90 |
"content": "<|ja|>",
|
| 91 |
"single_word": false,
|
| 92 |
"lstrip": false,
|
| 93 |
"rstrip": false,
|
| 94 |
+
"normalized": false
|
|
|
|
| 95 |
},
|
| 96 |
{
|
| 97 |
"id": 50266,
|
| 98 |
+
"special": true,
|
| 99 |
"content": "<|pt|>",
|
| 100 |
"single_word": false,
|
| 101 |
"lstrip": false,
|
| 102 |
"rstrip": false,
|
| 103 |
+
"normalized": false
|
|
|
|
| 104 |
},
|
| 105 |
{
|
| 106 |
"id": 50267,
|
| 107 |
+
"special": true,
|
| 108 |
"content": "<|tr|>",
|
| 109 |
"single_word": false,
|
| 110 |
"lstrip": false,
|
| 111 |
"rstrip": false,
|
| 112 |
+
"normalized": false
|
|
|
|
| 113 |
},
|
| 114 |
{
|
| 115 |
"id": 50268,
|
| 116 |
+
"special": true,
|
| 117 |
"content": "<|pl|>",
|
| 118 |
"single_word": false,
|
| 119 |
"lstrip": false,
|
| 120 |
"rstrip": false,
|
| 121 |
+
"normalized": false
|
|
|
|
| 122 |
},
|
| 123 |
{
|
| 124 |
"id": 50269,
|
| 125 |
+
"special": true,
|
| 126 |
"content": "<|ca|>",
|
| 127 |
"single_word": false,
|
| 128 |
"lstrip": false,
|
| 129 |
"rstrip": false,
|
| 130 |
+
"normalized": false
|
|
|
|
| 131 |
},
|
| 132 |
{
|
| 133 |
"id": 50270,
|
| 134 |
+
"special": true,
|
| 135 |
"content": "<|nl|>",
|
| 136 |
"single_word": false,
|
| 137 |
"lstrip": false,
|
| 138 |
"rstrip": false,
|
| 139 |
+
"normalized": false
|
|
|
|
| 140 |
},
|
| 141 |
{
|
| 142 |
"id": 50271,
|
| 143 |
+
"special": true,
|
| 144 |
"content": "<|ar|>",
|
| 145 |
"single_word": false,
|
| 146 |
"lstrip": false,
|
| 147 |
"rstrip": false,
|
| 148 |
+
"normalized": false
|
|
|
|
| 149 |
},
|
| 150 |
{
|
| 151 |
"id": 50272,
|
| 152 |
+
"special": true,
|
| 153 |
"content": "<|sv|>",
|
| 154 |
"single_word": false,
|
| 155 |
"lstrip": false,
|
| 156 |
"rstrip": false,
|
| 157 |
+
"normalized": false
|
|
|
|
| 158 |
},
|
| 159 |
{
|
| 160 |
"id": 50273,
|
| 161 |
+
"special": true,
|
| 162 |
"content": "<|it|>",
|
| 163 |
"single_word": false,
|
| 164 |
"lstrip": false,
|
| 165 |
"rstrip": false,
|
| 166 |
+
"normalized": false
|
|
|
|
| 167 |
},
|
| 168 |
{
|
| 169 |
"id": 50274,
|
| 170 |
+
"special": true,
|
| 171 |
"content": "<|id|>",
|
| 172 |
"single_word": false,
|
| 173 |
"lstrip": false,
|
| 174 |
"rstrip": false,
|
| 175 |
+
"normalized": false
|
|
|
|
| 176 |
},
|
| 177 |
{
|
| 178 |
"id": 50275,
|
| 179 |
+
"special": true,
|
| 180 |
"content": "<|hi|>",
|
| 181 |
"single_word": false,
|
| 182 |
"lstrip": false,
|
| 183 |
"rstrip": false,
|
| 184 |
+
"normalized": false
|
|
|
|
| 185 |
},
|
| 186 |
{
|
| 187 |
"id": 50276,
|
| 188 |
+
"special": true,
|
| 189 |
"content": "<|fi|>",
|
| 190 |
"single_word": false,
|
| 191 |
"lstrip": false,
|
| 192 |
"rstrip": false,
|
| 193 |
+
"normalized": false
|
|
|
|
| 194 |
},
|
| 195 |
{
|
| 196 |
"id": 50277,
|
| 197 |
+
"special": true,
|
| 198 |
"content": "<|vi|>",
|
| 199 |
"single_word": false,
|
| 200 |
"lstrip": false,
|
| 201 |
"rstrip": false,
|
| 202 |
+
"normalized": false
|
|
|
|
| 203 |
},
|
| 204 |
{
|
| 205 |
"id": 50278,
|
| 206 |
+
"special": true,
|
| 207 |
"content": "<|iw|>",
|
| 208 |
"single_word": false,
|
| 209 |
"lstrip": false,
|
| 210 |
"rstrip": false,
|
| 211 |
+
"normalized": false
|
|
|
|
| 212 |
},
|
| 213 |
{
|
| 214 |
"id": 50279,
|
| 215 |
+
"special": true,
|
| 216 |
"content": "<|uk|>",
|
| 217 |
"single_word": false,
|
| 218 |
"lstrip": false,
|
| 219 |
"rstrip": false,
|
| 220 |
+
"normalized": false
|
|
|
|
| 221 |
},
|
| 222 |
{
|
| 223 |
"id": 50280,
|
| 224 |
+
"special": true,
|
| 225 |
"content": "<|el|>",
|
| 226 |
"single_word": false,
|
| 227 |
"lstrip": false,
|
| 228 |
"rstrip": false,
|
| 229 |
+
"normalized": false
|
|
|
|
| 230 |
},
|
| 231 |
{
|
| 232 |
"id": 50281,
|
| 233 |
+
"special": true,
|
| 234 |
"content": "<|ms|>",
|
| 235 |
"single_word": false,
|
| 236 |
"lstrip": false,
|
| 237 |
"rstrip": false,
|
| 238 |
+
"normalized": false
|
|
|
|
| 239 |
},
|
| 240 |
{
|
| 241 |
"id": 50282,
|
| 242 |
+
"special": true,
|
| 243 |
"content": "<|cs|>",
|
| 244 |
"single_word": false,
|
| 245 |
"lstrip": false,
|
| 246 |
"rstrip": false,
|
| 247 |
+
"normalized": false
|
|
|
|
| 248 |
},
|
| 249 |
{
|
| 250 |
"id": 50283,
|
| 251 |
+
"special": true,
|
| 252 |
"content": "<|ro|>",
|
| 253 |
"single_word": false,
|
| 254 |
"lstrip": false,
|
| 255 |
"rstrip": false,
|
| 256 |
+
"normalized": false
|
|
|
|
| 257 |
},
|
| 258 |
{
|
| 259 |
"id": 50284,
|
| 260 |
+
"special": true,
|
| 261 |
"content": "<|da|>",
|
| 262 |
"single_word": false,
|
| 263 |
"lstrip": false,
|
| 264 |
"rstrip": false,
|
| 265 |
+
"normalized": false
|
|
|
|
| 266 |
},
|
| 267 |
{
|
| 268 |
"id": 50285,
|
| 269 |
+
"special": true,
|
| 270 |
"content": "<|hu|>",
|
| 271 |
"single_word": false,
|
| 272 |
"lstrip": false,
|
| 273 |
"rstrip": false,
|
| 274 |
+
"normalized": false
|
|
|
|
| 275 |
},
|
| 276 |
{
|
| 277 |
"id": 50286,
|
| 278 |
+
"special": true,
|
| 279 |
"content": "<|ta|>",
|
| 280 |
"single_word": false,
|
| 281 |
"lstrip": false,
|
| 282 |
"rstrip": false,
|
| 283 |
+
"normalized": false
|
|
|
|
| 284 |
},
|
| 285 |
{
|
| 286 |
"id": 50287,
|
| 287 |
+
"special": true,
|
| 288 |
"content": "<|no|>",
|
| 289 |
"single_word": false,
|
| 290 |
"lstrip": false,
|
| 291 |
"rstrip": false,
|
| 292 |
+
"normalized": false
|
|
|
|
| 293 |
},
|
| 294 |
{
|
| 295 |
"id": 50288,
|
| 296 |
+
"special": true,
|
| 297 |
"content": "<|th|>",
|
| 298 |
"single_word": false,
|
| 299 |
"lstrip": false,
|
| 300 |
"rstrip": false,
|
| 301 |
+
"normalized": false
|
|
|
|
| 302 |
},
|
| 303 |
{
|
| 304 |
"id": 50289,
|
| 305 |
+
"special": true,
|
| 306 |
"content": "<|ur|>",
|
| 307 |
"single_word": false,
|
| 308 |
"lstrip": false,
|
| 309 |
"rstrip": false,
|
| 310 |
+
"normalized": false
|
|
|
|
| 311 |
},
|
| 312 |
{
|
| 313 |
"id": 50290,
|
| 314 |
+
"special": true,
|
| 315 |
"content": "<|hr|>",
|
| 316 |
"single_word": false,
|
| 317 |
"lstrip": false,
|
| 318 |
"rstrip": false,
|
| 319 |
+
"normalized": false
|
|
|
|
| 320 |
},
|
| 321 |
{
|
| 322 |
"id": 50291,
|
| 323 |
+
"special": true,
|
| 324 |
"content": "<|bg|>",
|
| 325 |
"single_word": false,
|
| 326 |
"lstrip": false,
|
| 327 |
"rstrip": false,
|
| 328 |
+
"normalized": false
|
|
|
|
| 329 |
},
|
| 330 |
{
|
| 331 |
"id": 50292,
|
| 332 |
+
"special": true,
|
| 333 |
"content": "<|lt|>",
|
| 334 |
"single_word": false,
|
| 335 |
"lstrip": false,
|
| 336 |
"rstrip": false,
|
| 337 |
+
"normalized": false
|
|
|
|
| 338 |
},
|
| 339 |
{
|
| 340 |
"id": 50293,
|
| 341 |
+
"special": true,
|
| 342 |
"content": "<|la|>",
|
| 343 |
"single_word": false,
|
| 344 |
"lstrip": false,
|
| 345 |
"rstrip": false,
|
| 346 |
+
"normalized": false
|
|
|
|
| 347 |
},
|
| 348 |
{
|
| 349 |
"id": 50294,
|
| 350 |
+
"special": true,
|
| 351 |
"content": "<|mi|>",
|
| 352 |
"single_word": false,
|
| 353 |
"lstrip": false,
|
| 354 |
"rstrip": false,
|
| 355 |
+
"normalized": false
|
|
|
|
| 356 |
},
|
| 357 |
{
|
| 358 |
"id": 50295,
|
| 359 |
+
"special": true,
|
| 360 |
"content": "<|ml|>",
|
| 361 |
"single_word": false,
|
| 362 |
"lstrip": false,
|
| 363 |
"rstrip": false,
|
| 364 |
+
"normalized": false
|
|
|
|
| 365 |
},
|
| 366 |
{
|
| 367 |
"id": 50296,
|
| 368 |
+
"special": true,
|
| 369 |
"content": "<|cy|>",
|
| 370 |
"single_word": false,
|
| 371 |
"lstrip": false,
|
| 372 |
"rstrip": false,
|
| 373 |
+
"normalized": false
|
|
|
|
| 374 |
},
|
| 375 |
{
|
| 376 |
"id": 50297,
|
| 377 |
+
"special": true,
|
| 378 |
"content": "<|sk|>",
|
| 379 |
"single_word": false,
|
| 380 |
"lstrip": false,
|
| 381 |
"rstrip": false,
|
| 382 |
+
"normalized": false
|
|
|
|
| 383 |
},
|
| 384 |
{
|
| 385 |
"id": 50298,
|
| 386 |
+
"special": true,
|
| 387 |
"content": "<|te|>",
|
| 388 |
"single_word": false,
|
| 389 |
"lstrip": false,
|
| 390 |
"rstrip": false,
|
| 391 |
+
"normalized": false
|
|
|
|
| 392 |
},
|
| 393 |
{
|
| 394 |
"id": 50299,
|
| 395 |
+
"special": true,
|
| 396 |
"content": "<|fa|>",
|
| 397 |
"single_word": false,
|
| 398 |
"lstrip": false,
|
| 399 |
"rstrip": false,
|
| 400 |
+
"normalized": false
|
|
|
|
| 401 |
},
|
| 402 |
{
|
| 403 |
"id": 50300,
|
| 404 |
+
"special": true,
|
| 405 |
"content": "<|lv|>",
|
| 406 |
"single_word": false,
|
| 407 |
"lstrip": false,
|
| 408 |
"rstrip": false,
|
| 409 |
+
"normalized": false
|
|
|
|
| 410 |
},
|
| 411 |
{
|
| 412 |
"id": 50301,
|
| 413 |
+
"special": true,
|
| 414 |
"content": "<|bn|>",
|
| 415 |
"single_word": false,
|
| 416 |
"lstrip": false,
|
| 417 |
"rstrip": false,
|
| 418 |
+
"normalized": false
|
|
|
|
| 419 |
},
|
| 420 |
{
|
| 421 |
"id": 50302,
|
| 422 |
+
"special": true,
|
| 423 |
"content": "<|sr|>",
|
| 424 |
"single_word": false,
|
| 425 |
"lstrip": false,
|
| 426 |
"rstrip": false,
|
| 427 |
+
"normalized": false
|
|
|
|
| 428 |
},
|
| 429 |
{
|
| 430 |
"id": 50303,
|
| 431 |
+
"special": true,
|
| 432 |
"content": "<|az|>",
|
| 433 |
"single_word": false,
|
| 434 |
"lstrip": false,
|
| 435 |
"rstrip": false,
|
| 436 |
+
"normalized": false
|
|
|
|
| 437 |
},
|
| 438 |
{
|
| 439 |
"id": 50304,
|
| 440 |
+
"special": true,
|
| 441 |
"content": "<|sl|>",
|
| 442 |
"single_word": false,
|
| 443 |
"lstrip": false,
|
| 444 |
"rstrip": false,
|
| 445 |
+
"normalized": false
|
|
|
|
| 446 |
},
|
| 447 |
{
|
| 448 |
"id": 50305,
|
| 449 |
+
"special": true,
|
| 450 |
"content": "<|kn|>",
|
| 451 |
"single_word": false,
|
| 452 |
"lstrip": false,
|
| 453 |
"rstrip": false,
|
| 454 |
+
"normalized": false
|
|
|
|
| 455 |
},
|
| 456 |
{
|
| 457 |
"id": 50306,
|
| 458 |
+
"special": true,
|
| 459 |
"content": "<|et|>",
|
| 460 |
"single_word": false,
|
| 461 |
"lstrip": false,
|
| 462 |
"rstrip": false,
|
| 463 |
+
"normalized": false
|
|
|
|
| 464 |
},
|
| 465 |
{
|
| 466 |
"id": 50307,
|
| 467 |
+
"special": true,
|
| 468 |
"content": "<|mk|>",
|
| 469 |
"single_word": false,
|
| 470 |
"lstrip": false,
|
| 471 |
"rstrip": false,
|
| 472 |
+
"normalized": false
|
|
|
|
| 473 |
},
|
| 474 |
{
|
| 475 |
"id": 50308,
|
| 476 |
+
"special": true,
|
| 477 |
"content": "<|br|>",
|
| 478 |
"single_word": false,
|
| 479 |
"lstrip": false,
|
| 480 |
"rstrip": false,
|
| 481 |
+
"normalized": false
|
|
|
|
| 482 |
},
|
| 483 |
{
|
| 484 |
"id": 50309,
|
| 485 |
+
"special": true,
|
| 486 |
"content": "<|eu|>",
|
| 487 |
"single_word": false,
|
| 488 |
"lstrip": false,
|
| 489 |
"rstrip": false,
|
| 490 |
+
"normalized": false
|
|
|
|
| 491 |
},
|
| 492 |
{
|
| 493 |
"id": 50310,
|
| 494 |
+
"special": true,
|
| 495 |
"content": "<|is|>",
|
| 496 |
"single_word": false,
|
| 497 |
"lstrip": false,
|
| 498 |
"rstrip": false,
|
| 499 |
+
"normalized": false
|
|
|
|
| 500 |
},
|
| 501 |
{
|
| 502 |
"id": 50311,
|
| 503 |
+
"special": true,
|
| 504 |
"content": "<|hy|>",
|
| 505 |
"single_word": false,
|
| 506 |
"lstrip": false,
|
| 507 |
"rstrip": false,
|
| 508 |
+
"normalized": false
|
|
|
|
| 509 |
},
|
| 510 |
{
|
| 511 |
"id": 50312,
|
| 512 |
+
"special": true,
|
| 513 |
"content": "<|ne|>",
|
| 514 |
"single_word": false,
|
| 515 |
"lstrip": false,
|
| 516 |
"rstrip": false,
|
| 517 |
+
"normalized": false
|
|
|
|
| 518 |
},
|
| 519 |
{
|
| 520 |
"id": 50313,
|
| 521 |
+
"special": true,
|
| 522 |
"content": "<|mn|>",
|
| 523 |
"single_word": false,
|
| 524 |
"lstrip": false,
|
| 525 |
"rstrip": false,
|
| 526 |
+
"normalized": false
|
|
|
|
| 527 |
},
|
| 528 |
{
|
| 529 |
"id": 50314,
|
| 530 |
+
"special": true,
|
| 531 |
"content": "<|bs|>",
|
| 532 |
"single_word": false,
|
| 533 |
"lstrip": false,
|
| 534 |
"rstrip": false,
|
| 535 |
+
"normalized": false
|
|
|
|
| 536 |
},
|
| 537 |
{
|
| 538 |
"id": 50315,
|
| 539 |
+
"special": true,
|
| 540 |
"content": "<|kk|>",
|
| 541 |
"single_word": false,
|
| 542 |
"lstrip": false,
|
| 543 |
"rstrip": false,
|
| 544 |
+
"normalized": false
|
|
|
|
| 545 |
},
|
| 546 |
{
|
| 547 |
"id": 50316,
|
| 548 |
+
"special": true,
|
| 549 |
"content": "<|sq|>",
|
| 550 |
"single_word": false,
|
| 551 |
"lstrip": false,
|
| 552 |
"rstrip": false,
|
| 553 |
+
"normalized": false
|
|
|
|
| 554 |
},
|
| 555 |
{
|
| 556 |
"id": 50317,
|
| 557 |
+
"special": true,
|
| 558 |
"content": "<|sw|>",
|
| 559 |
"single_word": false,
|
| 560 |
"lstrip": false,
|
| 561 |
"rstrip": false,
|
| 562 |
+
"normalized": false
|
|
|
|
| 563 |
},
|
| 564 |
{
|
| 565 |
"id": 50318,
|
| 566 |
+
"special": true,
|
| 567 |
"content": "<|gl|>",
|
| 568 |
"single_word": false,
|
| 569 |
"lstrip": false,
|
| 570 |
"rstrip": false,
|
| 571 |
+
"normalized": false
|
|
|
|
| 572 |
},
|
| 573 |
{
|
| 574 |
"id": 50319,
|
| 575 |
+
"special": true,
|
| 576 |
"content": "<|mr|>",
|
| 577 |
"single_word": false,
|
| 578 |
"lstrip": false,
|
| 579 |
"rstrip": false,
|
| 580 |
+
"normalized": false
|
|
|
|
| 581 |
},
|
| 582 |
{
|
| 583 |
"id": 50320,
|
| 584 |
+
"special": true,
|
| 585 |
"content": "<|pa|>",
|
| 586 |
"single_word": false,
|
| 587 |
"lstrip": false,
|
| 588 |
"rstrip": false,
|
| 589 |
+
"normalized": false
|
|
|
|
| 590 |
},
|
| 591 |
{
|
| 592 |
"id": 50321,
|
| 593 |
+
"special": true,
|
| 594 |
"content": "<|si|>",
|
| 595 |
"single_word": false,
|
| 596 |
"lstrip": false,
|
| 597 |
"rstrip": false,
|
| 598 |
+
"normalized": false
|
|
|
|
| 599 |
},
|
| 600 |
{
|
| 601 |
"id": 50322,
|
| 602 |
+
"special": true,
|
| 603 |
"content": "<|km|>",
|
| 604 |
"single_word": false,
|
| 605 |
"lstrip": false,
|
| 606 |
"rstrip": false,
|
| 607 |
+
"normalized": false
|
|
|
|
| 608 |
},
|
| 609 |
{
|
| 610 |
"id": 50323,
|
| 611 |
+
"special": true,
|
| 612 |
"content": "<|sn|>",
|
| 613 |
"single_word": false,
|
| 614 |
"lstrip": false,
|
| 615 |
"rstrip": false,
|
| 616 |
+
"normalized": false
|
|
|
|
| 617 |
},
|
| 618 |
{
|
| 619 |
"id": 50324,
|
| 620 |
+
"special": true,
|
| 621 |
"content": "<|yo|>",
|
| 622 |
"single_word": false,
|
| 623 |
"lstrip": false,
|
| 624 |
"rstrip": false,
|
| 625 |
+
"normalized": false
|
|
|
|
| 626 |
},
|
| 627 |
{
|
| 628 |
"id": 50325,
|
| 629 |
+
"special": true,
|
| 630 |
"content": "<|so|>",
|
| 631 |
"single_word": false,
|
| 632 |
"lstrip": false,
|
| 633 |
"rstrip": false,
|
| 634 |
+
"normalized": false
|
|
|
|
| 635 |
},
|
| 636 |
{
|
| 637 |
"id": 50326,
|
| 638 |
+
"special": true,
|
| 639 |
"content": "<|af|>",
|
| 640 |
"single_word": false,
|
| 641 |
"lstrip": false,
|
| 642 |
"rstrip": false,
|
| 643 |
+
"normalized": false
|
|
|
|
| 644 |
},
|
| 645 |
{
|
| 646 |
"id": 50327,
|
| 647 |
+
"special": true,
|
| 648 |
"content": "<|oc|>",
|
| 649 |
"single_word": false,
|
| 650 |
"lstrip": false,
|
| 651 |
"rstrip": false,
|
| 652 |
+
"normalized": false
|
|
|
|
| 653 |
},
|
| 654 |
{
|
| 655 |
"id": 50328,
|
| 656 |
+
"special": true,
|
| 657 |
"content": "<|ka|>",
|
| 658 |
"single_word": false,
|
| 659 |
"lstrip": false,
|
| 660 |
"rstrip": false,
|
| 661 |
+
"normalized": false
|
|
|
|
| 662 |
},
|
| 663 |
{
|
| 664 |
"id": 50329,
|
| 665 |
+
"special": true,
|
| 666 |
"content": "<|be|>",
|
| 667 |
"single_word": false,
|
| 668 |
"lstrip": false,
|
| 669 |
"rstrip": false,
|
| 670 |
+
"normalized": false
|
|
|
|
| 671 |
},
|
| 672 |
{
|
| 673 |
"id": 50330,
|
| 674 |
+
"special": true,
|
| 675 |
"content": "<|tg|>",
|
| 676 |
"single_word": false,
|
| 677 |
"lstrip": false,
|
| 678 |
"rstrip": false,
|
| 679 |
+
"normalized": false
|
|
|
|
| 680 |
},
|
| 681 |
{
|
| 682 |
"id": 50331,
|
| 683 |
+
"special": true,
|
| 684 |
"content": "<|sd|>",
|
| 685 |
"single_word": false,
|
| 686 |
"lstrip": false,
|
| 687 |
"rstrip": false,
|
| 688 |
+
"normalized": false
|
|
|
|
| 689 |
},
|
| 690 |
{
|
| 691 |
"id": 50332,
|
| 692 |
+
"special": true,
|
| 693 |
"content": "<|gu|>",
|
| 694 |
"single_word": false,
|
| 695 |
"lstrip": false,
|
| 696 |
"rstrip": false,
|
| 697 |
+
"normalized": false
|
|
|
|
| 698 |
},
|
| 699 |
{
|
| 700 |
"id": 50333,
|
| 701 |
+
"special": true,
|
| 702 |
"content": "<|am|>",
|
| 703 |
"single_word": false,
|
| 704 |
"lstrip": false,
|
| 705 |
"rstrip": false,
|
| 706 |
+
"normalized": false
|
|
|
|
| 707 |
},
|
| 708 |
{
|
| 709 |
"id": 50334,
|
| 710 |
+
"special": true,
|
| 711 |
"content": "<|yi|>",
|
| 712 |
"single_word": false,
|
| 713 |
"lstrip": false,
|
| 714 |
"rstrip": false,
|
| 715 |
+
"normalized": false
|
|
|
|
| 716 |
},
|
| 717 |
{
|
| 718 |
"id": 50335,
|
| 719 |
+
"special": true,
|
| 720 |
"content": "<|lo|>",
|
| 721 |
"single_word": false,
|
| 722 |
"lstrip": false,
|
| 723 |
"rstrip": false,
|
| 724 |
+
"normalized": false
|
|
|
|
| 725 |
},
|
| 726 |
{
|
| 727 |
"id": 50336,
|
| 728 |
+
"special": true,
|
| 729 |
"content": "<|uz|>",
|
| 730 |
"single_word": false,
|
| 731 |
"lstrip": false,
|
| 732 |
"rstrip": false,
|
| 733 |
+
"normalized": false
|
|
|
|
| 734 |
},
|
| 735 |
{
|
| 736 |
"id": 50337,
|
| 737 |
+
"special": true,
|
| 738 |
"content": "<|fo|>",
|
| 739 |
"single_word": false,
|
| 740 |
"lstrip": false,
|
| 741 |
"rstrip": false,
|
| 742 |
+
"normalized": false
|
|
|
|
| 743 |
},
|
| 744 |
{
|
| 745 |
"id": 50338,
|
| 746 |
+
"special": true,
|
| 747 |
"content": "<|ht|>",
|
| 748 |
"single_word": false,
|
| 749 |
"lstrip": false,
|
| 750 |
"rstrip": false,
|
| 751 |
+
"normalized": false
|
|
|
|
| 752 |
},
|
| 753 |
{
|
| 754 |
"id": 50339,
|
| 755 |
+
"special": true,
|
| 756 |
"content": "<|ps|>",
|
| 757 |
"single_word": false,
|
| 758 |
"lstrip": false,
|
| 759 |
"rstrip": false,
|
| 760 |
+
"normalized": false
|
|
|
|
| 761 |
},
|
| 762 |
{
|
| 763 |
"id": 50340,
|
| 764 |
+
"special": true,
|
| 765 |
"content": "<|tk|>",
|
| 766 |
"single_word": false,
|
| 767 |
"lstrip": false,
|
| 768 |
"rstrip": false,
|
| 769 |
+
"normalized": false
|
|
|
|
| 770 |
},
|
| 771 |
{
|
| 772 |
"id": 50341,
|
| 773 |
+
"special": true,
|
| 774 |
"content": "<|nn|>",
|
| 775 |
"single_word": false,
|
| 776 |
"lstrip": false,
|
| 777 |
"rstrip": false,
|
| 778 |
+
"normalized": false
|
|
|
|
| 779 |
},
|
| 780 |
{
|
| 781 |
"id": 50342,
|
| 782 |
+
"special": true,
|
| 783 |
"content": "<|mt|>",
|
| 784 |
"single_word": false,
|
| 785 |
"lstrip": false,
|
| 786 |
"rstrip": false,
|
| 787 |
+
"normalized": false
|
|
|
|
| 788 |
},
|
| 789 |
{
|
| 790 |
"id": 50343,
|
| 791 |
+
"special": true,
|
| 792 |
"content": "<|sa|>",
|
| 793 |
"single_word": false,
|
| 794 |
"lstrip": false,
|
| 795 |
"rstrip": false,
|
| 796 |
+
"normalized": false
|
|
|
|
| 797 |
},
|
| 798 |
{
|
| 799 |
"id": 50344,
|
| 800 |
+
"special": true,
|
| 801 |
"content": "<|lb|>",
|
| 802 |
"single_word": false,
|
| 803 |
"lstrip": false,
|
| 804 |
"rstrip": false,
|
| 805 |
+
"normalized": false
|
|
|
|
| 806 |
},
|
| 807 |
{
|
| 808 |
"id": 50345,
|
| 809 |
+
"special": true,
|
| 810 |
"content": "<|my|>",
|
| 811 |
"single_word": false,
|
| 812 |
"lstrip": false,
|
| 813 |
"rstrip": false,
|
| 814 |
+
"normalized": false
|
|
|
|
| 815 |
},
|
| 816 |
{
|
| 817 |
"id": 50346,
|
| 818 |
+
"special": true,
|
| 819 |
"content": "<|bo|>",
|
| 820 |
"single_word": false,
|
| 821 |
"lstrip": false,
|
| 822 |
"rstrip": false,
|
| 823 |
+
"normalized": false
|
|
|
|
| 824 |
},
|
| 825 |
{
|
| 826 |
"id": 50347,
|
| 827 |
+
"special": true,
|
| 828 |
"content": "<|tl|>",
|
| 829 |
"single_word": false,
|
| 830 |
"lstrip": false,
|
| 831 |
"rstrip": false,
|
| 832 |
+
"normalized": false
|
|
|
|
| 833 |
},
|
| 834 |
{
|
| 835 |
"id": 50348,
|
| 836 |
+
"special": true,
|
| 837 |
"content": "<|mg|>",
|
| 838 |
"single_word": false,
|
| 839 |
"lstrip": false,
|
| 840 |
"rstrip": false,
|
| 841 |
+
"normalized": false
|
|
|
|
| 842 |
},
|
| 843 |
{
|
| 844 |
"id": 50349,
|
| 845 |
+
"special": true,
|
| 846 |
"content": "<|as|>",
|
| 847 |
"single_word": false,
|
| 848 |
"lstrip": false,
|
| 849 |
"rstrip": false,
|
| 850 |
+
"normalized": false
|
|
|
|
| 851 |
},
|
| 852 |
{
|
| 853 |
"id": 50350,
|
| 854 |
+
"special": true,
|
| 855 |
"content": "<|tt|>",
|
| 856 |
"single_word": false,
|
| 857 |
"lstrip": false,
|
| 858 |
"rstrip": false,
|
| 859 |
+
"normalized": false
|
|
|
|
| 860 |
},
|
| 861 |
{
|
| 862 |
"id": 50351,
|
| 863 |
+
"special": true,
|
| 864 |
"content": "<|haw|>",
|
| 865 |
"single_word": false,
|
| 866 |
"lstrip": false,
|
| 867 |
"rstrip": false,
|
| 868 |
+
"normalized": false
|
|
|
|
| 869 |
},
|
| 870 |
{
|
| 871 |
"id": 50352,
|
| 872 |
+
"special": true,
|
| 873 |
"content": "<|ln|>",
|
| 874 |
"single_word": false,
|
| 875 |
"lstrip": false,
|
| 876 |
"rstrip": false,
|
| 877 |
+
"normalized": false
|
|
|
|
| 878 |
},
|
| 879 |
{
|
| 880 |
"id": 50353,
|
| 881 |
+
"special": true,
|
| 882 |
"content": "<|ha|>",
|
| 883 |
"single_word": false,
|
| 884 |
"lstrip": false,
|
| 885 |
"rstrip": false,
|
| 886 |
+
"normalized": false
|
|
|
|
| 887 |
},
|
| 888 |
{
|
| 889 |
"id": 50354,
|
| 890 |
+
"special": true,
|
| 891 |
"content": "<|ba|>",
|
| 892 |
"single_word": false,
|
| 893 |
"lstrip": false,
|
| 894 |
"rstrip": false,
|
| 895 |
+
"normalized": false
|
|
|
|
| 896 |
},
|
| 897 |
{
|
| 898 |
"id": 50355,
|
| 899 |
+
"special": true,
|
| 900 |
"content": "<|jw|>",
|
| 901 |
"single_word": false,
|
| 902 |
"lstrip": false,
|
| 903 |
"rstrip": false,
|
| 904 |
+
"normalized": false
|
|
|
|
| 905 |
},
|
| 906 |
{
|
| 907 |
"id": 50356,
|
| 908 |
+
"special": true,
|
| 909 |
"content": "<|su|>",
|
| 910 |
"single_word": false,
|
| 911 |
"lstrip": false,
|
| 912 |
"rstrip": false,
|
| 913 |
+
"normalized": false
|
|
|
|
| 914 |
},
|
| 915 |
{
|
| 916 |
"id": 50357,
|
| 917 |
+
"special": true,
|
| 918 |
"content": "<|translate|>",
|
| 919 |
"single_word": false,
|
| 920 |
"lstrip": false,
|
| 921 |
"rstrip": false,
|
| 922 |
+
"normalized": false
|
|
|
|
| 923 |
},
|
| 924 |
{
|
| 925 |
"id": 50358,
|
| 926 |
+
"special": true,
|
| 927 |
"content": "<|transcribe|>",
|
| 928 |
"single_word": false,
|
| 929 |
"lstrip": false,
|
| 930 |
"rstrip": false,
|
| 931 |
+
"normalized": false
|
|
|
|
| 932 |
},
|
| 933 |
{
|
| 934 |
"id": 50359,
|
| 935 |
+
"special": true,
|
| 936 |
"content": "<|startoflm|>",
|
| 937 |
"single_word": false,
|
| 938 |
"lstrip": false,
|
| 939 |
"rstrip": false,
|
| 940 |
+
"normalized": false
|
|
|
|
| 941 |
},
|
| 942 |
{
|
| 943 |
"id": 50360,
|
| 944 |
+
"special": true,
|
| 945 |
"content": "<|startofprev|>",
|
| 946 |
"single_word": false,
|
| 947 |
"lstrip": false,
|
| 948 |
"rstrip": false,
|
| 949 |
+
"normalized": false
|
|
|
|
| 950 |
},
|
| 951 |
{
|
| 952 |
"id": 50361,
|
| 953 |
+
"special": true,
|
| 954 |
"content": "<|nocaptions|>",
|
| 955 |
"single_word": false,
|
| 956 |
"lstrip": false,
|
| 957 |
"rstrip": false,
|
| 958 |
+
"normalized": false
|
|
|
|
| 959 |
},
|
| 960 |
{
|
| 961 |
"id": 50362,
|
| 962 |
+
"special": true,
|
| 963 |
"content": "<|notimestamps|>",
|
| 964 |
"single_word": false,
|
| 965 |
"lstrip": false,
|
| 966 |
"rstrip": false,
|
| 967 |
+
"normalized": false
|
|
|
|
| 968 |
}
|
| 969 |
],
|
| 970 |
"normalizer": null,
|
| 971 |
"pre_tokenizer": {
|
| 972 |
"type": "ByteLevel",
|
| 973 |
"add_prefix_space": false,
|
| 974 |
+
"trim_offsets": true
|
|
|
|
| 975 |
},
|
| 976 |
"post_processor": {
|
| 977 |
"type": "TemplateProcessing",
|
|
|
|
| 1066 |
"decoder": {
|
| 1067 |
"type": "ByteLevel",
|
| 1068 |
"add_prefix_space": true,
|
| 1069 |
+
"trim_offsets": true
|
|
|
|
| 1070 |
},
|
| 1071 |
"model": {
|
| 1072 |
"type": "BPE",
|
quantized/openai/whisper-base.en/speech2seq-lm-with-past/tokenizer_config.json
CHANGED
|
@@ -19,7 +19,6 @@
|
|
| 19 |
},
|
| 20 |
"errors": "replace",
|
| 21 |
"model_max_length": 1024,
|
| 22 |
-
"name_or_path": "openai/whisper-base.en",
|
| 23 |
"pad_token": null,
|
| 24 |
"processor_class": "WhisperProcessor",
|
| 25 |
"return_attention_mask": false,
|
|
|
|
| 19 |
},
|
| 20 |
"errors": "replace",
|
| 21 |
"model_max_length": 1024,
|
|
|
|
| 22 |
"pad_token": null,
|
| 23 |
"processor_class": "WhisperProcessor",
|
| 24 |
"return_attention_mask": false,
|
quantized/openai/whisper-base.en/speech2seq-lm-with-past/vocab.json
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
quantized/openai/whisper-base/default/config.json
CHANGED
|
@@ -2,6 +2,7 @@
|
|
| 2 |
"_name_or_path": "openai/whisper-base",
|
| 3 |
"activation_dropout": 0.0,
|
| 4 |
"activation_function": "gelu",
|
|
|
|
| 5 |
"architectures": [
|
| 6 |
"WhisperForConditionalGeneration"
|
| 7 |
],
|
|
@@ -11,6 +12,7 @@
|
|
| 11 |
50257
|
| 12 |
],
|
| 13 |
"bos_token_id": 50257,
|
|
|
|
| 14 |
"d_model": 512,
|
| 15 |
"decoder_attention_heads": 8,
|
| 16 |
"decoder_ffn_dim": 2048,
|
|
@@ -39,6 +41,12 @@
|
|
| 39 |
],
|
| 40 |
"init_std": 0.02,
|
| 41 |
"is_encoder_decoder": true,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 42 |
"max_length": 448,
|
| 43 |
"max_source_positions": 1500,
|
| 44 |
"max_target_positions": 448,
|
|
@@ -135,7 +143,8 @@
|
|
| 135 |
50361,
|
| 136 |
50362
|
| 137 |
],
|
| 138 |
-
"transformers_version": "4.
|
| 139 |
"use_cache": true,
|
|
|
|
| 140 |
"vocab_size": 51865
|
| 141 |
}
|
|
|
|
| 2 |
"_name_or_path": "openai/whisper-base",
|
| 3 |
"activation_dropout": 0.0,
|
| 4 |
"activation_function": "gelu",
|
| 5 |
+
"apply_spec_augment": false,
|
| 6 |
"architectures": [
|
| 7 |
"WhisperForConditionalGeneration"
|
| 8 |
],
|
|
|
|
| 12 |
50257
|
| 13 |
],
|
| 14 |
"bos_token_id": 50257,
|
| 15 |
+
"classifier_proj_size": 256,
|
| 16 |
"d_model": 512,
|
| 17 |
"decoder_attention_heads": 8,
|
| 18 |
"decoder_ffn_dim": 2048,
|
|
|
|
| 41 |
],
|
| 42 |
"init_std": 0.02,
|
| 43 |
"is_encoder_decoder": true,
|
| 44 |
+
"mask_feature_length": 10,
|
| 45 |
+
"mask_feature_min_masks": 0,
|
| 46 |
+
"mask_feature_prob": 0.0,
|
| 47 |
+
"mask_time_length": 10,
|
| 48 |
+
"mask_time_min_masks": 2,
|
| 49 |
+
"mask_time_prob": 0.05,
|
| 50 |
"max_length": 448,
|
| 51 |
"max_source_positions": 1500,
|
| 52 |
"max_target_positions": 448,
|
|
|
|
| 143 |
50361,
|
| 144 |
50362
|
| 145 |
],
|
| 146 |
+
"transformers_version": "4.27.2",
|
| 147 |
"use_cache": true,
|
| 148 |
+
"use_weighted_layer_sum": false,
|
| 149 |
"vocab_size": 51865
|
| 150 |
}
|
quantized/openai/whisper-base/default/generation_config.json
DELETED
|
@@ -1,219 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"begin_suppress_tokens": [
|
| 3 |
-
220,
|
| 4 |
-
50257
|
| 5 |
-
],
|
| 6 |
-
"bos_token_id": 50257,
|
| 7 |
-
"decoder_start_token_id": 50258,
|
| 8 |
-
"eos_token_id": 50257,
|
| 9 |
-
"forced_decoder_ids": [
|
| 10 |
-
[
|
| 11 |
-
1,
|
| 12 |
-
null
|
| 13 |
-
],
|
| 14 |
-
[
|
| 15 |
-
2,
|
| 16 |
-
50359
|
| 17 |
-
]
|
| 18 |
-
],
|
| 19 |
-
"is_multilingual": true,
|
| 20 |
-
"lang_to_id": {
|
| 21 |
-
"<|af|>": 50327,
|
| 22 |
-
"<|am|>": 50334,
|
| 23 |
-
"<|ar|>": 50272,
|
| 24 |
-
"<|as|>": 50350,
|
| 25 |
-
"<|az|>": 50304,
|
| 26 |
-
"<|ba|>": 50355,
|
| 27 |
-
"<|be|>": 50330,
|
| 28 |
-
"<|bg|>": 50292,
|
| 29 |
-
"<|bn|>": 50302,
|
| 30 |
-
"<|bo|>": 50347,
|
| 31 |
-
"<|br|>": 50309,
|
| 32 |
-
"<|bs|>": 50315,
|
| 33 |
-
"<|ca|>": 50270,
|
| 34 |
-
"<|cs|>": 50283,
|
| 35 |
-
"<|cy|>": 50297,
|
| 36 |
-
"<|da|>": 50285,
|
| 37 |
-
"<|de|>": 50261,
|
| 38 |
-
"<|el|>": 50281,
|
| 39 |
-
"<|en|>": 50259,
|
| 40 |
-
"<|es|>": 50262,
|
| 41 |
-
"<|et|>": 50307,
|
| 42 |
-
"<|eu|>": 50310,
|
| 43 |
-
"<|fa|>": 50300,
|
| 44 |
-
"<|fi|>": 50277,
|
| 45 |
-
"<|fo|>": 50338,
|
| 46 |
-
"<|fr|>": 50265,
|
| 47 |
-
"<|gl|>": 50319,
|
| 48 |
-
"<|gu|>": 50333,
|
| 49 |
-
"<|haw|>": 50352,
|
| 50 |
-
"<|ha|>": 50354,
|
| 51 |
-
"<|he|>": 50279,
|
| 52 |
-
"<|hi|>": 50276,
|
| 53 |
-
"<|hr|>": 50291,
|
| 54 |
-
"<|ht|>": 50339,
|
| 55 |
-
"<|hu|>": 50286,
|
| 56 |
-
"<|hy|>": 50312,
|
| 57 |
-
"<|id|>": 50275,
|
| 58 |
-
"<|is|>": 50311,
|
| 59 |
-
"<|it|>": 50274,
|
| 60 |
-
"<|ja|>": 50266,
|
| 61 |
-
"<|jw|>": 50356,
|
| 62 |
-
"<|ka|>": 50329,
|
| 63 |
-
"<|kk|>": 50316,
|
| 64 |
-
"<|km|>": 50323,
|
| 65 |
-
"<|kn|>": 50306,
|
| 66 |
-
"<|ko|>": 50264,
|
| 67 |
-
"<|la|>": 50294,
|
| 68 |
-
"<|lb|>": 50345,
|
| 69 |
-
"<|ln|>": 50353,
|
| 70 |
-
"<|lo|>": 50336,
|
| 71 |
-
"<|lt|>": 50293,
|
| 72 |
-
"<|lv|>": 50301,
|
| 73 |
-
"<|mg|>": 50349,
|
| 74 |
-
"<|mi|>": 50295,
|
| 75 |
-
"<|mk|>": 50308,
|
| 76 |
-
"<|ml|>": 50296,
|
| 77 |
-
"<|mn|>": 50314,
|
| 78 |
-
"<|mr|>": 50320,
|
| 79 |
-
"<|ms|>": 50282,
|
| 80 |
-
"<|mt|>": 50343,
|
| 81 |
-
"<|my|>": 50346,
|
| 82 |
-
"<|ne|>": 50313,
|
| 83 |
-
"<|nl|>": 50271,
|
| 84 |
-
"<|nn|>": 50342,
|
| 85 |
-
"<|no|>": 50288,
|
| 86 |
-
"<|oc|>": 50328,
|
| 87 |
-
"<|pa|>": 50321,
|
| 88 |
-
"<|pl|>": 50269,
|
| 89 |
-
"<|ps|>": 50340,
|
| 90 |
-
"<|pt|>": 50267,
|
| 91 |
-
"<|ro|>": 50284,
|
| 92 |
-
"<|ru|>": 50263,
|
| 93 |
-
"<|sa|>": 50344,
|
| 94 |
-
"<|sd|>": 50332,
|
| 95 |
-
"<|si|>": 50322,
|
| 96 |
-
"<|sk|>": 50298,
|
| 97 |
-
"<|sl|>": 50305,
|
| 98 |
-
"<|sn|>": 50324,
|
| 99 |
-
"<|so|>": 50326,
|
| 100 |
-
"<|sq|>": 50317,
|
| 101 |
-
"<|sr|>": 50303,
|
| 102 |
-
"<|su|>": 50357,
|
| 103 |
-
"<|sv|>": 50273,
|
| 104 |
-
"<|sw|>": 50318,
|
| 105 |
-
"<|ta|>": 50287,
|
| 106 |
-
"<|te|>": 50299,
|
| 107 |
-
"<|tg|>": 50331,
|
| 108 |
-
"<|th|>": 50289,
|
| 109 |
-
"<|tk|>": 50341,
|
| 110 |
-
"<|tl|>": 50348,
|
| 111 |
-
"<|tr|>": 50268,
|
| 112 |
-
"<|tt|>": 50351,
|
| 113 |
-
"<|uk|>": 50280,
|
| 114 |
-
"<|ur|>": 50290,
|
| 115 |
-
"<|uz|>": 50337,
|
| 116 |
-
"<|vi|>": 50278,
|
| 117 |
-
"<|yi|>": 50335,
|
| 118 |
-
"<|yo|>": 50325,
|
| 119 |
-
"<|zh|>": 50260
|
| 120 |
-
},
|
| 121 |
-
"max_initial_timestamp_index": 1,
|
| 122 |
-
"max_length": 448,
|
| 123 |
-
"no_timestamps_token_id": 50363,
|
| 124 |
-
"pad_token_id": 50257,
|
| 125 |
-
"return_timestamps": false,
|
| 126 |
-
"suppress_tokens": [
|
| 127 |
-
1,
|
| 128 |
-
2,
|
| 129 |
-
7,
|
| 130 |
-
8,
|
| 131 |
-
9,
|
| 132 |
-
10,
|
| 133 |
-
14,
|
| 134 |
-
25,
|
| 135 |
-
26,
|
| 136 |
-
27,
|
| 137 |
-
28,
|
| 138 |
-
29,
|
| 139 |
-
31,
|
| 140 |
-
58,
|
| 141 |
-
59,
|
| 142 |
-
60,
|
| 143 |
-
61,
|
| 144 |
-
62,
|
| 145 |
-
63,
|
| 146 |
-
90,
|
| 147 |
-
91,
|
| 148 |
-
92,
|
| 149 |
-
93,
|
| 150 |
-
359,
|
| 151 |
-
503,
|
| 152 |
-
522,
|
| 153 |
-
542,
|
| 154 |
-
873,
|
| 155 |
-
893,
|
| 156 |
-
902,
|
| 157 |
-
918,
|
| 158 |
-
922,
|
| 159 |
-
931,
|
| 160 |
-
1350,
|
| 161 |
-
1853,
|
| 162 |
-
1982,
|
| 163 |
-
2460,
|
| 164 |
-
2627,
|
| 165 |
-
3246,
|
| 166 |
-
3253,
|
| 167 |
-
3268,
|
| 168 |
-
3536,
|
| 169 |
-
3846,
|
| 170 |
-
3961,
|
| 171 |
-
4183,
|
| 172 |
-
4667,
|
| 173 |
-
6585,
|
| 174 |
-
6647,
|
| 175 |
-
7273,
|
| 176 |
-
9061,
|
| 177 |
-
9383,
|
| 178 |
-
10428,
|
| 179 |
-
10929,
|
| 180 |
-
11938,
|
| 181 |
-
12033,
|
| 182 |
-
12331,
|
| 183 |
-
12562,
|
| 184 |
-
13793,
|
| 185 |
-
14157,
|
| 186 |
-
14635,
|
| 187 |
-
15265,
|
| 188 |
-
15618,
|
| 189 |
-
16553,
|
| 190 |
-
16604,
|
| 191 |
-
18362,
|
| 192 |
-
18956,
|
| 193 |
-
20075,
|
| 194 |
-
21675,
|
| 195 |
-
22520,
|
| 196 |
-
26130,
|
| 197 |
-
26161,
|
| 198 |
-
26435,
|
| 199 |
-
28279,
|
| 200 |
-
29464,
|
| 201 |
-
31650,
|
| 202 |
-
32302,
|
| 203 |
-
32470,
|
| 204 |
-
36865,
|
| 205 |
-
42863,
|
| 206 |
-
47425,
|
| 207 |
-
49870,
|
| 208 |
-
50254,
|
| 209 |
-
50258,
|
| 210 |
-
50360,
|
| 211 |
-
50361,
|
| 212 |
-
50362
|
| 213 |
-
],
|
| 214 |
-
"task_to_id": {
|
| 215 |
-
"transcribe": 50359,
|
| 216 |
-
"translate": 50358
|
| 217 |
-
},
|
| 218 |
-
"transformers_version": "4.27.0.dev0"
|
| 219 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
quantized/openai/whisper-base/default/merges.txt
CHANGED
|
@@ -1,4 +1,4 @@
|
|
| 1 |
-
#version: 0.2
|
| 2 |
Ġ a
|
| 3 |
Ġt h
|
| 4 |
i n
|
|
|
|
| 1 |
+
#version: 0.2 - Trained by `huggingface/tokenizers`
|
| 2 |
Ġ a
|
| 3 |
Ġt h
|
| 4 |
i n
|
quantized/openai/{whisper-base.en/default/encoder_model.onnx → whisper-base/default/model.onnx}
RENAMED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fc8ec8a5545484b07635fb781c0e7b590af576c6a0068bdbf298227ddf6bed16
|
| 3 |
+
size 76779199
|
quantized/openai/whisper-base/default/tokenizer.json
CHANGED
|
@@ -5,974 +5,973 @@
|
|
| 5 |
"added_tokens": [
|
| 6 |
{
|
| 7 |
"id": 50257,
|
|
|
|
| 8 |
"content": "<|endoftext|>",
|
| 9 |
"single_word": false,
|
| 10 |
"lstrip": false,
|
| 11 |
"rstrip": false,
|
| 12 |
-
"normalized": false
|
| 13 |
-
"special": true
|
| 14 |
},
|
| 15 |
{
|
| 16 |
"id": 50258,
|
|
|
|
| 17 |
"content": "<|startoftranscript|>",
|
| 18 |
"single_word": false,
|
| 19 |
"lstrip": false,
|
| 20 |
"rstrip": false,
|
| 21 |
-
"normalized": false
|
| 22 |
-
"special": true
|
| 23 |
},
|
| 24 |
{
|
| 25 |
"id": 50259,
|
|
|
|
| 26 |
"content": "<|en|>",
|
| 27 |
"single_word": false,
|
| 28 |
"lstrip": false,
|
| 29 |
"rstrip": false,
|
| 30 |
-
"normalized": false
|
| 31 |
-
"special": true
|
| 32 |
},
|
| 33 |
{
|
| 34 |
"id": 50260,
|
|
|
|
| 35 |
"content": "<|zh|>",
|
| 36 |
"single_word": false,
|
| 37 |
"lstrip": false,
|
| 38 |
"rstrip": false,
|
| 39 |
-
"normalized": false
|
| 40 |
-
"special": true
|
| 41 |
},
|
| 42 |
{
|
| 43 |
"id": 50261,
|
|
|
|
| 44 |
"content": "<|de|>",
|
| 45 |
"single_word": false,
|
| 46 |
"lstrip": false,
|
| 47 |
"rstrip": false,
|
| 48 |
-
"normalized": false
|
| 49 |
-
"special": true
|
| 50 |
},
|
| 51 |
{
|
| 52 |
"id": 50262,
|
|
|
|
| 53 |
"content": "<|es|>",
|
| 54 |
"single_word": false,
|
| 55 |
"lstrip": false,
|
| 56 |
"rstrip": false,
|
| 57 |
-
"normalized": false
|
| 58 |
-
"special": true
|
| 59 |
},
|
| 60 |
{
|
| 61 |
"id": 50263,
|
|
|
|
| 62 |
"content": "<|ru|>",
|
| 63 |
"single_word": false,
|
| 64 |
"lstrip": false,
|
| 65 |
"rstrip": false,
|
| 66 |
-
"normalized": false
|
| 67 |
-
"special": true
|
| 68 |
},
|
| 69 |
{
|
| 70 |
"id": 50264,
|
|
|
|
| 71 |
"content": "<|ko|>",
|
| 72 |
"single_word": false,
|
| 73 |
"lstrip": false,
|
| 74 |
"rstrip": false,
|
| 75 |
-
"normalized": false
|
| 76 |
-
"special": true
|
| 77 |
},
|
| 78 |
{
|
| 79 |
"id": 50265,
|
|
|
|
| 80 |
"content": "<|fr|>",
|
| 81 |
"single_word": false,
|
| 82 |
"lstrip": false,
|
| 83 |
"rstrip": false,
|
| 84 |
-
"normalized": false
|
| 85 |
-
"special": true
|
| 86 |
},
|
| 87 |
{
|
| 88 |
"id": 50266,
|
|
|
|
| 89 |
"content": "<|ja|>",
|
| 90 |
"single_word": false,
|
| 91 |
"lstrip": false,
|
| 92 |
"rstrip": false,
|
| 93 |
-
"normalized": false
|
| 94 |
-
"special": true
|
| 95 |
},
|
| 96 |
{
|
| 97 |
"id": 50267,
|
|
|
|
| 98 |
"content": "<|pt|>",
|
| 99 |
"single_word": false,
|
| 100 |
"lstrip": false,
|
| 101 |
"rstrip": false,
|
| 102 |
-
"normalized": false
|
| 103 |
-
"special": true
|
| 104 |
},
|
| 105 |
{
|
| 106 |
"id": 50268,
|
|
|
|
| 107 |
"content": "<|tr|>",
|
| 108 |
"single_word": false,
|
| 109 |
"lstrip": false,
|
| 110 |
"rstrip": false,
|
| 111 |
-
"normalized": false
|
| 112 |
-
"special": true
|
| 113 |
},
|
| 114 |
{
|
| 115 |
"id": 50269,
|
|
|
|
| 116 |
"content": "<|pl|>",
|
| 117 |
"single_word": false,
|
| 118 |
"lstrip": false,
|
| 119 |
"rstrip": false,
|
| 120 |
-
"normalized": false
|
| 121 |
-
"special": true
|
| 122 |
},
|
| 123 |
{
|
| 124 |
"id": 50270,
|
|
|
|
| 125 |
"content": "<|ca|>",
|
| 126 |
"single_word": false,
|
| 127 |
"lstrip": false,
|
| 128 |
"rstrip": false,
|
| 129 |
-
"normalized": false
|
| 130 |
-
"special": true
|
| 131 |
},
|
| 132 |
{
|
| 133 |
"id": 50271,
|
|
|
|
| 134 |
"content": "<|nl|>",
|
| 135 |
"single_word": false,
|
| 136 |
"lstrip": false,
|
| 137 |
"rstrip": false,
|
| 138 |
-
"normalized": false
|
| 139 |
-
"special": true
|
| 140 |
},
|
| 141 |
{
|
| 142 |
"id": 50272,
|
|
|
|
| 143 |
"content": "<|ar|>",
|
| 144 |
"single_word": false,
|
| 145 |
"lstrip": false,
|
| 146 |
"rstrip": false,
|
| 147 |
-
"normalized": false
|
| 148 |
-
"special": true
|
| 149 |
},
|
| 150 |
{
|
| 151 |
"id": 50273,
|
|
|
|
| 152 |
"content": "<|sv|>",
|
| 153 |
"single_word": false,
|
| 154 |
"lstrip": false,
|
| 155 |
"rstrip": false,
|
| 156 |
-
"normalized": false
|
| 157 |
-
"special": true
|
| 158 |
},
|
| 159 |
{
|
| 160 |
"id": 50274,
|
|
|
|
| 161 |
"content": "<|it|>",
|
| 162 |
"single_word": false,
|
| 163 |
"lstrip": false,
|
| 164 |
"rstrip": false,
|
| 165 |
-
"normalized": false
|
| 166 |
-
"special": true
|
| 167 |
},
|
| 168 |
{
|
| 169 |
"id": 50275,
|
|
|
|
| 170 |
"content": "<|id|>",
|
| 171 |
"single_word": false,
|
| 172 |
"lstrip": false,
|
| 173 |
"rstrip": false,
|
| 174 |
-
"normalized": false
|
| 175 |
-
"special": true
|
| 176 |
},
|
| 177 |
{
|
| 178 |
"id": 50276,
|
|
|
|
| 179 |
"content": "<|hi|>",
|
| 180 |
"single_word": false,
|
| 181 |
"lstrip": false,
|
| 182 |
"rstrip": false,
|
| 183 |
-
"normalized": false
|
| 184 |
-
"special": true
|
| 185 |
},
|
| 186 |
{
|
| 187 |
"id": 50277,
|
|
|
|
| 188 |
"content": "<|fi|>",
|
| 189 |
"single_word": false,
|
| 190 |
"lstrip": false,
|
| 191 |
"rstrip": false,
|
| 192 |
-
"normalized": false
|
| 193 |
-
"special": true
|
| 194 |
},
|
| 195 |
{
|
| 196 |
"id": 50278,
|
|
|
|
| 197 |
"content": "<|vi|>",
|
| 198 |
"single_word": false,
|
| 199 |
"lstrip": false,
|
| 200 |
"rstrip": false,
|
| 201 |
-
"normalized": false
|
| 202 |
-
"special": true
|
| 203 |
},
|
| 204 |
{
|
| 205 |
"id": 50279,
|
|
|
|
| 206 |
"content": "<|he|>",
|
| 207 |
"single_word": false,
|
| 208 |
"lstrip": false,
|
| 209 |
"rstrip": false,
|
| 210 |
-
"normalized": false
|
| 211 |
-
"special": true
|
| 212 |
},
|
| 213 |
{
|
| 214 |
"id": 50280,
|
|
|
|
| 215 |
"content": "<|uk|>",
|
| 216 |
"single_word": false,
|
| 217 |
"lstrip": false,
|
| 218 |
"rstrip": false,
|
| 219 |
-
"normalized": false
|
| 220 |
-
"special": true
|
| 221 |
},
|
| 222 |
{
|
| 223 |
"id": 50281,
|
|
|
|
| 224 |
"content": "<|el|>",
|
| 225 |
"single_word": false,
|
| 226 |
"lstrip": false,
|
| 227 |
"rstrip": false,
|
| 228 |
-
"normalized": false
|
| 229 |
-
"special": true
|
| 230 |
},
|
| 231 |
{
|
| 232 |
"id": 50282,
|
|
|
|
| 233 |
"content": "<|ms|>",
|
| 234 |
"single_word": false,
|
| 235 |
"lstrip": false,
|
| 236 |
"rstrip": false,
|
| 237 |
-
"normalized": false
|
| 238 |
-
"special": true
|
| 239 |
},
|
| 240 |
{
|
| 241 |
"id": 50283,
|
|
|
|
| 242 |
"content": "<|cs|>",
|
| 243 |
"single_word": false,
|
| 244 |
"lstrip": false,
|
| 245 |
"rstrip": false,
|
| 246 |
-
"normalized": false
|
| 247 |
-
"special": true
|
| 248 |
},
|
| 249 |
{
|
| 250 |
"id": 50284,
|
|
|
|
| 251 |
"content": "<|ro|>",
|
| 252 |
"single_word": false,
|
| 253 |
"lstrip": false,
|
| 254 |
"rstrip": false,
|
| 255 |
-
"normalized": false
|
| 256 |
-
"special": true
|
| 257 |
},
|
| 258 |
{
|
| 259 |
"id": 50285,
|
|
|
|
| 260 |
"content": "<|da|>",
|
| 261 |
"single_word": false,
|
| 262 |
"lstrip": false,
|
| 263 |
"rstrip": false,
|
| 264 |
-
"normalized": false
|
| 265 |
-
"special": true
|
| 266 |
},
|
| 267 |
{
|
| 268 |
"id": 50286,
|
|
|
|
| 269 |
"content": "<|hu|>",
|
| 270 |
"single_word": false,
|
| 271 |
"lstrip": false,
|
| 272 |
"rstrip": false,
|
| 273 |
-
"normalized": false
|
| 274 |
-
"special": true
|
| 275 |
},
|
| 276 |
{
|
| 277 |
"id": 50287,
|
|
|
|
| 278 |
"content": "<|ta|>",
|
| 279 |
"single_word": false,
|
| 280 |
"lstrip": false,
|
| 281 |
"rstrip": false,
|
| 282 |
-
"normalized": false
|
| 283 |
-
"special": true
|
| 284 |
},
|
| 285 |
{
|
| 286 |
"id": 50288,
|
|
|
|
| 287 |
"content": "<|no|>",
|
| 288 |
"single_word": false,
|
| 289 |
"lstrip": false,
|
| 290 |
"rstrip": false,
|
| 291 |
-
"normalized": false
|
| 292 |
-
"special": true
|
| 293 |
},
|
| 294 |
{
|
| 295 |
"id": 50289,
|
|
|
|
| 296 |
"content": "<|th|>",
|
| 297 |
"single_word": false,
|
| 298 |
"lstrip": false,
|
| 299 |
"rstrip": false,
|
| 300 |
-
"normalized": false
|
| 301 |
-
"special": true
|
| 302 |
},
|
| 303 |
{
|
| 304 |
"id": 50290,
|
|
|
|
| 305 |
"content": "<|ur|>",
|
| 306 |
"single_word": false,
|
| 307 |
"lstrip": false,
|
| 308 |
"rstrip": false,
|
| 309 |
-
"normalized": false
|
| 310 |
-
"special": true
|
| 311 |
},
|
| 312 |
{
|
| 313 |
"id": 50291,
|
|
|
|
| 314 |
"content": "<|hr|>",
|
| 315 |
"single_word": false,
|
| 316 |
"lstrip": false,
|
| 317 |
"rstrip": false,
|
| 318 |
-
"normalized": false
|
| 319 |
-
"special": true
|
| 320 |
},
|
| 321 |
{
|
| 322 |
"id": 50292,
|
|
|
|
| 323 |
"content": "<|bg|>",
|
| 324 |
"single_word": false,
|
| 325 |
"lstrip": false,
|
| 326 |
"rstrip": false,
|
| 327 |
-
"normalized": false
|
| 328 |
-
"special": true
|
| 329 |
},
|
| 330 |
{
|
| 331 |
"id": 50293,
|
|
|
|
| 332 |
"content": "<|lt|>",
|
| 333 |
"single_word": false,
|
| 334 |
"lstrip": false,
|
| 335 |
"rstrip": false,
|
| 336 |
-
"normalized": false
|
| 337 |
-
"special": true
|
| 338 |
},
|
| 339 |
{
|
| 340 |
"id": 50294,
|
|
|
|
| 341 |
"content": "<|la|>",
|
| 342 |
"single_word": false,
|
| 343 |
"lstrip": false,
|
| 344 |
"rstrip": false,
|
| 345 |
-
"normalized": false
|
| 346 |
-
"special": true
|
| 347 |
},
|
| 348 |
{
|
| 349 |
"id": 50295,
|
|
|
|
| 350 |
"content": "<|mi|>",
|
| 351 |
"single_word": false,
|
| 352 |
"lstrip": false,
|
| 353 |
"rstrip": false,
|
| 354 |
-
"normalized": false
|
| 355 |
-
"special": true
|
| 356 |
},
|
| 357 |
{
|
| 358 |
"id": 50296,
|
|
|
|
| 359 |
"content": "<|ml|>",
|
| 360 |
"single_word": false,
|
| 361 |
"lstrip": false,
|
| 362 |
"rstrip": false,
|
| 363 |
-
"normalized": false
|
| 364 |
-
"special": true
|
| 365 |
},
|
| 366 |
{
|
| 367 |
"id": 50297,
|
|
|
|
| 368 |
"content": "<|cy|>",
|
| 369 |
"single_word": false,
|
| 370 |
"lstrip": false,
|
| 371 |
"rstrip": false,
|
| 372 |
-
"normalized": false
|
| 373 |
-
"special": true
|
| 374 |
},
|
| 375 |
{
|
| 376 |
"id": 50298,
|
|
|
|
| 377 |
"content": "<|sk|>",
|
| 378 |
"single_word": false,
|
| 379 |
"lstrip": false,
|
| 380 |
"rstrip": false,
|
| 381 |
-
"normalized": false
|
| 382 |
-
"special": true
|
| 383 |
},
|
| 384 |
{
|
| 385 |
"id": 50299,
|
|
|
|
| 386 |
"content": "<|te|>",
|
| 387 |
"single_word": false,
|
| 388 |
"lstrip": false,
|
| 389 |
"rstrip": false,
|
| 390 |
-
"normalized": false
|
| 391 |
-
"special": true
|
| 392 |
},
|
| 393 |
{
|
| 394 |
"id": 50300,
|
|
|
|
| 395 |
"content": "<|fa|>",
|
| 396 |
"single_word": false,
|
| 397 |
"lstrip": false,
|
| 398 |
"rstrip": false,
|
| 399 |
-
"normalized": false
|
| 400 |
-
"special": true
|
| 401 |
},
|
| 402 |
{
|
| 403 |
"id": 50301,
|
|
|
|
| 404 |
"content": "<|lv|>",
|
| 405 |
"single_word": false,
|
| 406 |
"lstrip": false,
|
| 407 |
"rstrip": false,
|
| 408 |
-
"normalized": false
|
| 409 |
-
"special": true
|
| 410 |
},
|
| 411 |
{
|
| 412 |
"id": 50302,
|
|
|
|
| 413 |
"content": "<|bn|>",
|
| 414 |
"single_word": false,
|
| 415 |
"lstrip": false,
|
| 416 |
"rstrip": false,
|
| 417 |
-
"normalized": false
|
| 418 |
-
"special": true
|
| 419 |
},
|
| 420 |
{
|
| 421 |
"id": 50303,
|
|
|
|
| 422 |
"content": "<|sr|>",
|
| 423 |
"single_word": false,
|
| 424 |
"lstrip": false,
|
| 425 |
"rstrip": false,
|
| 426 |
-
"normalized": false
|
| 427 |
-
"special": true
|
| 428 |
},
|
| 429 |
{
|
| 430 |
"id": 50304,
|
|
|
|
| 431 |
"content": "<|az|>",
|
| 432 |
"single_word": false,
|
| 433 |
"lstrip": false,
|
| 434 |
"rstrip": false,
|
| 435 |
-
"normalized": false
|
| 436 |
-
"special": true
|
| 437 |
},
|
| 438 |
{
|
| 439 |
"id": 50305,
|
|
|
|
| 440 |
"content": "<|sl|>",
|
| 441 |
"single_word": false,
|
| 442 |
"lstrip": false,
|
| 443 |
"rstrip": false,
|
| 444 |
-
"normalized": false
|
| 445 |
-
"special": true
|
| 446 |
},
|
| 447 |
{
|
| 448 |
"id": 50306,
|
|
|
|
| 449 |
"content": "<|kn|>",
|
| 450 |
"single_word": false,
|
| 451 |
"lstrip": false,
|
| 452 |
"rstrip": false,
|
| 453 |
-
"normalized": false
|
| 454 |
-
"special": true
|
| 455 |
},
|
| 456 |
{
|
| 457 |
"id": 50307,
|
|
|
|
| 458 |
"content": "<|et|>",
|
| 459 |
"single_word": false,
|
| 460 |
"lstrip": false,
|
| 461 |
"rstrip": false,
|
| 462 |
-
"normalized": false
|
| 463 |
-
"special": true
|
| 464 |
},
|
| 465 |
{
|
| 466 |
"id": 50308,
|
|
|
|
| 467 |
"content": "<|mk|>",
|
| 468 |
"single_word": false,
|
| 469 |
"lstrip": false,
|
| 470 |
"rstrip": false,
|
| 471 |
-
"normalized": false
|
| 472 |
-
"special": true
|
| 473 |
},
|
| 474 |
{
|
| 475 |
"id": 50309,
|
|
|
|
| 476 |
"content": "<|br|>",
|
| 477 |
"single_word": false,
|
| 478 |
"lstrip": false,
|
| 479 |
"rstrip": false,
|
| 480 |
-
"normalized": false
|
| 481 |
-
"special": true
|
| 482 |
},
|
| 483 |
{
|
| 484 |
"id": 50310,
|
|
|
|
| 485 |
"content": "<|eu|>",
|
| 486 |
"single_word": false,
|
| 487 |
"lstrip": false,
|
| 488 |
"rstrip": false,
|
| 489 |
-
"normalized": false
|
| 490 |
-
"special": true
|
| 491 |
},
|
| 492 |
{
|
| 493 |
"id": 50311,
|
|
|
|
| 494 |
"content": "<|is|>",
|
| 495 |
"single_word": false,
|
| 496 |
"lstrip": false,
|
| 497 |
"rstrip": false,
|
| 498 |
-
"normalized": false
|
| 499 |
-
"special": true
|
| 500 |
},
|
| 501 |
{
|
| 502 |
"id": 50312,
|
|
|
|
| 503 |
"content": "<|hy|>",
|
| 504 |
"single_word": false,
|
| 505 |
"lstrip": false,
|
| 506 |
"rstrip": false,
|
| 507 |
-
"normalized": false
|
| 508 |
-
"special": true
|
| 509 |
},
|
| 510 |
{
|
| 511 |
"id": 50313,
|
|
|
|
| 512 |
"content": "<|ne|>",
|
| 513 |
"single_word": false,
|
| 514 |
"lstrip": false,
|
| 515 |
"rstrip": false,
|
| 516 |
-
"normalized": false
|
| 517 |
-
"special": true
|
| 518 |
},
|
| 519 |
{
|
| 520 |
"id": 50314,
|
|
|
|
| 521 |
"content": "<|mn|>",
|
| 522 |
"single_word": false,
|
| 523 |
"lstrip": false,
|
| 524 |
"rstrip": false,
|
| 525 |
-
"normalized": false
|
| 526 |
-
"special": true
|
| 527 |
},
|
| 528 |
{
|
| 529 |
"id": 50315,
|
|
|
|
| 530 |
"content": "<|bs|>",
|
| 531 |
"single_word": false,
|
| 532 |
"lstrip": false,
|
| 533 |
"rstrip": false,
|
| 534 |
-
"normalized": false
|
| 535 |
-
"special": true
|
| 536 |
},
|
| 537 |
{
|
| 538 |
"id": 50316,
|
|
|
|
| 539 |
"content": "<|kk|>",
|
| 540 |
"single_word": false,
|
| 541 |
"lstrip": false,
|
| 542 |
"rstrip": false,
|
| 543 |
-
"normalized": false
|
| 544 |
-
"special": true
|
| 545 |
},
|
| 546 |
{
|
| 547 |
"id": 50317,
|
|
|
|
| 548 |
"content": "<|sq|>",
|
| 549 |
"single_word": false,
|
| 550 |
"lstrip": false,
|
| 551 |
"rstrip": false,
|
| 552 |
-
"normalized": false
|
| 553 |
-
"special": true
|
| 554 |
},
|
| 555 |
{
|
| 556 |
"id": 50318,
|
|
|
|
| 557 |
"content": "<|sw|>",
|
| 558 |
"single_word": false,
|
| 559 |
"lstrip": false,
|
| 560 |
"rstrip": false,
|
| 561 |
-
"normalized": false
|
| 562 |
-
"special": true
|
| 563 |
},
|
| 564 |
{
|
| 565 |
"id": 50319,
|
|
|
|
| 566 |
"content": "<|gl|>",
|
| 567 |
"single_word": false,
|
| 568 |
"lstrip": false,
|
| 569 |
"rstrip": false,
|
| 570 |
-
"normalized": false
|
| 571 |
-
"special": true
|
| 572 |
},
|
| 573 |
{
|
| 574 |
"id": 50320,
|
|
|
|
| 575 |
"content": "<|mr|>",
|
| 576 |
"single_word": false,
|
| 577 |
"lstrip": false,
|
| 578 |
"rstrip": false,
|
| 579 |
-
"normalized": false
|
| 580 |
-
"special": true
|
| 581 |
},
|
| 582 |
{
|
| 583 |
"id": 50321,
|
|
|
|
| 584 |
"content": "<|pa|>",
|
| 585 |
"single_word": false,
|
| 586 |
"lstrip": false,
|
| 587 |
"rstrip": false,
|
| 588 |
-
"normalized": false
|
| 589 |
-
"special": true
|
| 590 |
},
|
| 591 |
{
|
| 592 |
"id": 50322,
|
|
|
|
| 593 |
"content": "<|si|>",
|
| 594 |
"single_word": false,
|
| 595 |
"lstrip": false,
|
| 596 |
"rstrip": false,
|
| 597 |
-
"normalized": false
|
| 598 |
-
"special": true
|
| 599 |
},
|
| 600 |
{
|
| 601 |
"id": 50323,
|
|
|
|
| 602 |
"content": "<|km|>",
|
| 603 |
"single_word": false,
|
| 604 |
"lstrip": false,
|
| 605 |
"rstrip": false,
|
| 606 |
-
"normalized": false
|
| 607 |
-
"special": true
|
| 608 |
},
|
| 609 |
{
|
| 610 |
"id": 50324,
|
|
|
|
| 611 |
"content": "<|sn|>",
|
| 612 |
"single_word": false,
|
| 613 |
"lstrip": false,
|
| 614 |
"rstrip": false,
|
| 615 |
-
"normalized": false
|
| 616 |
-
"special": true
|
| 617 |
},
|
| 618 |
{
|
| 619 |
"id": 50325,
|
|
|
|
| 620 |
"content": "<|yo|>",
|
| 621 |
"single_word": false,
|
| 622 |
"lstrip": false,
|
| 623 |
"rstrip": false,
|
| 624 |
-
"normalized": false
|
| 625 |
-
"special": true
|
| 626 |
},
|
| 627 |
{
|
| 628 |
"id": 50326,
|
|
|
|
| 629 |
"content": "<|so|>",
|
| 630 |
"single_word": false,
|
| 631 |
"lstrip": false,
|
| 632 |
"rstrip": false,
|
| 633 |
-
"normalized": false
|
| 634 |
-
"special": true
|
| 635 |
},
|
| 636 |
{
|
| 637 |
"id": 50327,
|
|
|
|
| 638 |
"content": "<|af|>",
|
| 639 |
"single_word": false,
|
| 640 |
"lstrip": false,
|
| 641 |
"rstrip": false,
|
| 642 |
-
"normalized": false
|
| 643 |
-
"special": true
|
| 644 |
},
|
| 645 |
{
|
| 646 |
"id": 50328,
|
|
|
|
| 647 |
"content": "<|oc|>",
|
| 648 |
"single_word": false,
|
| 649 |
"lstrip": false,
|
| 650 |
"rstrip": false,
|
| 651 |
-
"normalized": false
|
| 652 |
-
"special": true
|
| 653 |
},
|
| 654 |
{
|
| 655 |
"id": 50329,
|
|
|
|
| 656 |
"content": "<|ka|>",
|
| 657 |
"single_word": false,
|
| 658 |
"lstrip": false,
|
| 659 |
"rstrip": false,
|
| 660 |
-
"normalized": false
|
| 661 |
-
"special": true
|
| 662 |
},
|
| 663 |
{
|
| 664 |
"id": 50330,
|
|
|
|
| 665 |
"content": "<|be|>",
|
| 666 |
"single_word": false,
|
| 667 |
"lstrip": false,
|
| 668 |
"rstrip": false,
|
| 669 |
-
"normalized": false
|
| 670 |
-
"special": true
|
| 671 |
},
|
| 672 |
{
|
| 673 |
"id": 50331,
|
|
|
|
| 674 |
"content": "<|tg|>",
|
| 675 |
"single_word": false,
|
| 676 |
"lstrip": false,
|
| 677 |
"rstrip": false,
|
| 678 |
-
"normalized": false
|
| 679 |
-
"special": true
|
| 680 |
},
|
| 681 |
{
|
| 682 |
"id": 50332,
|
|
|
|
| 683 |
"content": "<|sd|>",
|
| 684 |
"single_word": false,
|
| 685 |
"lstrip": false,
|
| 686 |
"rstrip": false,
|
| 687 |
-
"normalized": false
|
| 688 |
-
"special": true
|
| 689 |
},
|
| 690 |
{
|
| 691 |
"id": 50333,
|
|
|
|
| 692 |
"content": "<|gu|>",
|
| 693 |
"single_word": false,
|
| 694 |
"lstrip": false,
|
| 695 |
"rstrip": false,
|
| 696 |
-
"normalized": false
|
| 697 |
-
"special": true
|
| 698 |
},
|
| 699 |
{
|
| 700 |
"id": 50334,
|
|
|
|
| 701 |
"content": "<|am|>",
|
| 702 |
"single_word": false,
|
| 703 |
"lstrip": false,
|
| 704 |
"rstrip": false,
|
| 705 |
-
"normalized": false
|
| 706 |
-
"special": true
|
| 707 |
},
|
| 708 |
{
|
| 709 |
"id": 50335,
|
|
|
|
| 710 |
"content": "<|yi|>",
|
| 711 |
"single_word": false,
|
| 712 |
"lstrip": false,
|
| 713 |
"rstrip": false,
|
| 714 |
-
"normalized": false
|
| 715 |
-
"special": true
|
| 716 |
},
|
| 717 |
{
|
| 718 |
"id": 50336,
|
|
|
|
| 719 |
"content": "<|lo|>",
|
| 720 |
"single_word": false,
|
| 721 |
"lstrip": false,
|
| 722 |
"rstrip": false,
|
| 723 |
-
"normalized": false
|
| 724 |
-
"special": true
|
| 725 |
},
|
| 726 |
{
|
| 727 |
"id": 50337,
|
|
|
|
| 728 |
"content": "<|uz|>",
|
| 729 |
"single_word": false,
|
| 730 |
"lstrip": false,
|
| 731 |
"rstrip": false,
|
| 732 |
-
"normalized": false
|
| 733 |
-
"special": true
|
| 734 |
},
|
| 735 |
{
|
| 736 |
"id": 50338,
|
|
|
|
| 737 |
"content": "<|fo|>",
|
| 738 |
"single_word": false,
|
| 739 |
"lstrip": false,
|
| 740 |
"rstrip": false,
|
| 741 |
-
"normalized": false
|
| 742 |
-
"special": true
|
| 743 |
},
|
| 744 |
{
|
| 745 |
"id": 50339,
|
|
|
|
| 746 |
"content": "<|ht|>",
|
| 747 |
"single_word": false,
|
| 748 |
"lstrip": false,
|
| 749 |
"rstrip": false,
|
| 750 |
-
"normalized": false
|
| 751 |
-
"special": true
|
| 752 |
},
|
| 753 |
{
|
| 754 |
"id": 50340,
|
|
|
|
| 755 |
"content": "<|ps|>",
|
| 756 |
"single_word": false,
|
| 757 |
"lstrip": false,
|
| 758 |
"rstrip": false,
|
| 759 |
-
"normalized": false
|
| 760 |
-
"special": true
|
| 761 |
},
|
| 762 |
{
|
| 763 |
"id": 50341,
|
|
|
|
| 764 |
"content": "<|tk|>",
|
| 765 |
"single_word": false,
|
| 766 |
"lstrip": false,
|
| 767 |
"rstrip": false,
|
| 768 |
-
"normalized": false
|
| 769 |
-
"special": true
|
| 770 |
},
|
| 771 |
{
|
| 772 |
"id": 50342,
|
|
|
|
| 773 |
"content": "<|nn|>",
|
| 774 |
"single_word": false,
|
| 775 |
"lstrip": false,
|
| 776 |
"rstrip": false,
|
| 777 |
-
"normalized": false
|
| 778 |
-
"special": true
|
| 779 |
},
|
| 780 |
{
|
| 781 |
"id": 50343,
|
|
|
|
| 782 |
"content": "<|mt|>",
|
| 783 |
"single_word": false,
|
| 784 |
"lstrip": false,
|
| 785 |
"rstrip": false,
|
| 786 |
-
"normalized": false
|
| 787 |
-
"special": true
|
| 788 |
},
|
| 789 |
{
|
| 790 |
"id": 50344,
|
|
|
|
| 791 |
"content": "<|sa|>",
|
| 792 |
"single_word": false,
|
| 793 |
"lstrip": false,
|
| 794 |
"rstrip": false,
|
| 795 |
-
"normalized": false
|
| 796 |
-
"special": true
|
| 797 |
},
|
| 798 |
{
|
| 799 |
"id": 50345,
|
|
|
|
| 800 |
"content": "<|lb|>",
|
| 801 |
"single_word": false,
|
| 802 |
"lstrip": false,
|
| 803 |
"rstrip": false,
|
| 804 |
-
"normalized": false
|
| 805 |
-
"special": true
|
| 806 |
},
|
| 807 |
{
|
| 808 |
"id": 50346,
|
|
|
|
| 809 |
"content": "<|my|>",
|
| 810 |
"single_word": false,
|
| 811 |
"lstrip": false,
|
| 812 |
"rstrip": false,
|
| 813 |
-
"normalized": false
|
| 814 |
-
"special": true
|
| 815 |
},
|
| 816 |
{
|
| 817 |
"id": 50347,
|
|
|
|
| 818 |
"content": "<|bo|>",
|
| 819 |
"single_word": false,
|
| 820 |
"lstrip": false,
|
| 821 |
"rstrip": false,
|
| 822 |
-
"normalized": false
|
| 823 |
-
"special": true
|
| 824 |
},
|
| 825 |
{
|
| 826 |
"id": 50348,
|
|
|
|
| 827 |
"content": "<|tl|>",
|
| 828 |
"single_word": false,
|
| 829 |
"lstrip": false,
|
| 830 |
"rstrip": false,
|
| 831 |
-
"normalized": false
|
| 832 |
-
"special": true
|
| 833 |
},
|
| 834 |
{
|
| 835 |
"id": 50349,
|
|
|
|
| 836 |
"content": "<|mg|>",
|
| 837 |
"single_word": false,
|
| 838 |
"lstrip": false,
|
| 839 |
"rstrip": false,
|
| 840 |
-
"normalized": false
|
| 841 |
-
"special": true
|
| 842 |
},
|
| 843 |
{
|
| 844 |
"id": 50350,
|
|
|
|
| 845 |
"content": "<|as|>",
|
| 846 |
"single_word": false,
|
| 847 |
"lstrip": false,
|
| 848 |
"rstrip": false,
|
| 849 |
-
"normalized": false
|
| 850 |
-
"special": true
|
| 851 |
},
|
| 852 |
{
|
| 853 |
"id": 50351,
|
|
|
|
| 854 |
"content": "<|tt|>",
|
| 855 |
"single_word": false,
|
| 856 |
"lstrip": false,
|
| 857 |
"rstrip": false,
|
| 858 |
-
"normalized": false
|
| 859 |
-
"special": true
|
| 860 |
},
|
| 861 |
{
|
| 862 |
"id": 50352,
|
|
|
|
| 863 |
"content": "<|haw|>",
|
| 864 |
"single_word": false,
|
| 865 |
"lstrip": false,
|
| 866 |
"rstrip": false,
|
| 867 |
-
"normalized": false
|
| 868 |
-
"special": true
|
| 869 |
},
|
| 870 |
{
|
| 871 |
"id": 50353,
|
|
|
|
| 872 |
"content": "<|ln|>",
|
| 873 |
"single_word": false,
|
| 874 |
"lstrip": false,
|
| 875 |
"rstrip": false,
|
| 876 |
-
"normalized": false
|
| 877 |
-
"special": true
|
| 878 |
},
|
| 879 |
{
|
| 880 |
"id": 50354,
|
|
|
|
| 881 |
"content": "<|ha|>",
|
| 882 |
"single_word": false,
|
| 883 |
"lstrip": false,
|
| 884 |
"rstrip": false,
|
| 885 |
-
"normalized": false
|
| 886 |
-
"special": true
|
| 887 |
},
|
| 888 |
{
|
| 889 |
"id": 50355,
|
|
|
|
| 890 |
"content": "<|ba|>",
|
| 891 |
"single_word": false,
|
| 892 |
"lstrip": false,
|
| 893 |
"rstrip": false,
|
| 894 |
-
"normalized": false
|
| 895 |
-
"special": true
|
| 896 |
},
|
| 897 |
{
|
| 898 |
"id": 50356,
|
|
|
|
| 899 |
"content": "<|jw|>",
|
| 900 |
"single_word": false,
|
| 901 |
"lstrip": false,
|
| 902 |
"rstrip": false,
|
| 903 |
-
"normalized": false
|
| 904 |
-
"special": true
|
| 905 |
},
|
| 906 |
{
|
| 907 |
"id": 50357,
|
|
|
|
| 908 |
"content": "<|su|>",
|
| 909 |
"single_word": false,
|
| 910 |
"lstrip": false,
|
| 911 |
"rstrip": false,
|
| 912 |
-
"normalized": false
|
| 913 |
-
"special": true
|
| 914 |
},
|
| 915 |
{
|
| 916 |
"id": 50358,
|
|
|
|
| 917 |
"content": "<|translate|>",
|
| 918 |
"single_word": false,
|
| 919 |
"lstrip": false,
|
| 920 |
"rstrip": false,
|
| 921 |
-
"normalized": false
|
| 922 |
-
"special": true
|
| 923 |
},
|
| 924 |
{
|
| 925 |
"id": 50359,
|
|
|
|
| 926 |
"content": "<|transcribe|>",
|
| 927 |
"single_word": false,
|
| 928 |
"lstrip": false,
|
| 929 |
"rstrip": false,
|
| 930 |
-
"normalized": false
|
| 931 |
-
"special": true
|
| 932 |
},
|
| 933 |
{
|
| 934 |
"id": 50360,
|
|
|
|
| 935 |
"content": "<|startoflm|>",
|
| 936 |
"single_word": false,
|
| 937 |
"lstrip": false,
|
| 938 |
"rstrip": false,
|
| 939 |
-
"normalized": false
|
| 940 |
-
"special": true
|
| 941 |
},
|
| 942 |
{
|
| 943 |
"id": 50361,
|
|
|
|
| 944 |
"content": "<|startofprev|>",
|
| 945 |
"single_word": false,
|
| 946 |
"lstrip": false,
|
| 947 |
"rstrip": false,
|
| 948 |
-
"normalized": false
|
| 949 |
-
"special": true
|
| 950 |
},
|
| 951 |
{
|
| 952 |
"id": 50362,
|
|
|
|
| 953 |
"content": "<|nocaptions|>",
|
| 954 |
"single_word": false,
|
| 955 |
"lstrip": false,
|
| 956 |
"rstrip": false,
|
| 957 |
-
"normalized": false
|
| 958 |
-
"special": true
|
| 959 |
},
|
| 960 |
{
|
| 961 |
"id": 50363,
|
|
|
|
| 962 |
"content": "<|notimestamps|>",
|
| 963 |
"single_word": false,
|
| 964 |
"lstrip": false,
|
| 965 |
"rstrip": false,
|
| 966 |
-
"normalized": false
|
| 967 |
-
"special": true
|
| 968 |
}
|
| 969 |
],
|
| 970 |
"normalizer": null,
|
| 971 |
"pre_tokenizer": {
|
| 972 |
"type": "ByteLevel",
|
| 973 |
"add_prefix_space": false,
|
| 974 |
-
"trim_offsets": true
|
| 975 |
-
"use_regex": true
|
| 976 |
},
|
| 977 |
"post_processor": {
|
| 978 |
"type": "TemplateProcessing",
|
|
@@ -1067,8 +1066,7 @@
|
|
| 1067 |
"decoder": {
|
| 1068 |
"type": "ByteLevel",
|
| 1069 |
"add_prefix_space": true,
|
| 1070 |
-
"trim_offsets": true
|
| 1071 |
-
"use_regex": true
|
| 1072 |
},
|
| 1073 |
"model": {
|
| 1074 |
"type": "BPE",
|
|
|
|
| 5 |
"added_tokens": [
|
| 6 |
{
|
| 7 |
"id": 50257,
|
| 8 |
+
"special": true,
|
| 9 |
"content": "<|endoftext|>",
|
| 10 |
"single_word": false,
|
| 11 |
"lstrip": false,
|
| 12 |
"rstrip": false,
|
| 13 |
+
"normalized": false
|
|
|
|
| 14 |
},
|
| 15 |
{
|
| 16 |
"id": 50258,
|
| 17 |
+
"special": true,
|
| 18 |
"content": "<|startoftranscript|>",
|
| 19 |
"single_word": false,
|
| 20 |
"lstrip": false,
|
| 21 |
"rstrip": false,
|
| 22 |
+
"normalized": false
|
|
|
|
| 23 |
},
|
| 24 |
{
|
| 25 |
"id": 50259,
|
| 26 |
+
"special": true,
|
| 27 |
"content": "<|en|>",
|
| 28 |
"single_word": false,
|
| 29 |
"lstrip": false,
|
| 30 |
"rstrip": false,
|
| 31 |
+
"normalized": false
|
|
|
|
| 32 |
},
|
| 33 |
{
|
| 34 |
"id": 50260,
|
| 35 |
+
"special": true,
|
| 36 |
"content": "<|zh|>",
|
| 37 |
"single_word": false,
|
| 38 |
"lstrip": false,
|
| 39 |
"rstrip": false,
|
| 40 |
+
"normalized": false
|
|
|
|
| 41 |
},
|
| 42 |
{
|
| 43 |
"id": 50261,
|
| 44 |
+
"special": true,
|
| 45 |
"content": "<|de|>",
|
| 46 |
"single_word": false,
|
| 47 |
"lstrip": false,
|
| 48 |
"rstrip": false,
|
| 49 |
+
"normalized": false
|
|
|
|
| 50 |
},
|
| 51 |
{
|
| 52 |
"id": 50262,
|
| 53 |
+
"special": true,
|
| 54 |
"content": "<|es|>",
|
| 55 |
"single_word": false,
|
| 56 |
"lstrip": false,
|
| 57 |
"rstrip": false,
|
| 58 |
+
"normalized": false
|
|
|
|
| 59 |
},
|
| 60 |
{
|
| 61 |
"id": 50263,
|
| 62 |
+
"special": true,
|
| 63 |
"content": "<|ru|>",
|
| 64 |
"single_word": false,
|
| 65 |
"lstrip": false,
|
| 66 |
"rstrip": false,
|
| 67 |
+
"normalized": false
|
|
|
|
| 68 |
},
|
| 69 |
{
|
| 70 |
"id": 50264,
|
| 71 |
+
"special": true,
|
| 72 |
"content": "<|ko|>",
|
| 73 |
"single_word": false,
|
| 74 |
"lstrip": false,
|
| 75 |
"rstrip": false,
|
| 76 |
+
"normalized": false
|
|
|
|
| 77 |
},
|
| 78 |
{
|
| 79 |
"id": 50265,
|
| 80 |
+
"special": true,
|
| 81 |
"content": "<|fr|>",
|
| 82 |
"single_word": false,
|
| 83 |
"lstrip": false,
|
| 84 |
"rstrip": false,
|
| 85 |
+
"normalized": false
|
|
|
|
| 86 |
},
|
| 87 |
{
|
| 88 |
"id": 50266,
|
| 89 |
+
"special": true,
|
| 90 |
"content": "<|ja|>",
|
| 91 |
"single_word": false,
|
| 92 |
"lstrip": false,
|
| 93 |
"rstrip": false,
|
| 94 |
+
"normalized": false
|
|
|
|
| 95 |
},
|
| 96 |
{
|
| 97 |
"id": 50267,
|
| 98 |
+
"special": true,
|
| 99 |
"content": "<|pt|>",
|
| 100 |
"single_word": false,
|
| 101 |
"lstrip": false,
|
| 102 |
"rstrip": false,
|
| 103 |
+
"normalized": false
|
|
|
|
| 104 |
},
|
| 105 |
{
|
| 106 |
"id": 50268,
|
| 107 |
+
"special": true,
|
| 108 |
"content": "<|tr|>",
|
| 109 |
"single_word": false,
|
| 110 |
"lstrip": false,
|
| 111 |
"rstrip": false,
|
| 112 |
+
"normalized": false
|
|
|
|
| 113 |
},
|
| 114 |
{
|
| 115 |
"id": 50269,
|
| 116 |
+
"special": true,
|
| 117 |
"content": "<|pl|>",
|
| 118 |
"single_word": false,
|
| 119 |
"lstrip": false,
|
| 120 |
"rstrip": false,
|
| 121 |
+
"normalized": false
|
|
|
|
| 122 |
},
|
| 123 |
{
|
| 124 |
"id": 50270,
|
| 125 |
+
"special": true,
|
| 126 |
"content": "<|ca|>",
|
| 127 |
"single_word": false,
|
| 128 |
"lstrip": false,
|
| 129 |
"rstrip": false,
|
| 130 |
+
"normalized": false
|
|
|
|
| 131 |
},
|
| 132 |
{
|
| 133 |
"id": 50271,
|
| 134 |
+
"special": true,
|
| 135 |
"content": "<|nl|>",
|
| 136 |
"single_word": false,
|
| 137 |
"lstrip": false,
|
| 138 |
"rstrip": false,
|
| 139 |
+
"normalized": false
|
|
|
|
| 140 |
},
|
| 141 |
{
|
| 142 |
"id": 50272,
|
| 143 |
+
"special": true,
|
| 144 |
"content": "<|ar|>",
|
| 145 |
"single_word": false,
|
| 146 |
"lstrip": false,
|
| 147 |
"rstrip": false,
|
| 148 |
+
"normalized": false
|
|
|
|
| 149 |
},
|
| 150 |
{
|
| 151 |
"id": 50273,
|
| 152 |
+
"special": true,
|
| 153 |
"content": "<|sv|>",
|
| 154 |
"single_word": false,
|
| 155 |
"lstrip": false,
|
| 156 |
"rstrip": false,
|
| 157 |
+
"normalized": false
|
|
|
|
| 158 |
},
|
| 159 |
{
|
| 160 |
"id": 50274,
|
| 161 |
+
"special": true,
|
| 162 |
"content": "<|it|>",
|
| 163 |
"single_word": false,
|
| 164 |
"lstrip": false,
|
| 165 |
"rstrip": false,
|
| 166 |
+
"normalized": false
|
|
|
|
| 167 |
},
|
| 168 |
{
|
| 169 |
"id": 50275,
|
| 170 |
+
"special": true,
|
| 171 |
"content": "<|id|>",
|
| 172 |
"single_word": false,
|
| 173 |
"lstrip": false,
|
| 174 |
"rstrip": false,
|
| 175 |
+
"normalized": false
|
|
|
|
| 176 |
},
|
| 177 |
{
|
| 178 |
"id": 50276,
|
| 179 |
+
"special": true,
|
| 180 |
"content": "<|hi|>",
|
| 181 |
"single_word": false,
|
| 182 |
"lstrip": false,
|
| 183 |
"rstrip": false,
|
| 184 |
+
"normalized": false
|
|
|
|
| 185 |
},
|
| 186 |
{
|
| 187 |
"id": 50277,
|
| 188 |
+
"special": true,
|
| 189 |
"content": "<|fi|>",
|
| 190 |
"single_word": false,
|
| 191 |
"lstrip": false,
|
| 192 |
"rstrip": false,
|
| 193 |
+
"normalized": false
|
|
|
|
| 194 |
},
|
| 195 |
{
|
| 196 |
"id": 50278,
|
| 197 |
+
"special": true,
|
| 198 |
"content": "<|vi|>",
|
| 199 |
"single_word": false,
|
| 200 |
"lstrip": false,
|
| 201 |
"rstrip": false,
|
| 202 |
+
"normalized": false
|
|
|
|
| 203 |
},
|
| 204 |
{
|
| 205 |
"id": 50279,
|
| 206 |
+
"special": true,
|
| 207 |
"content": "<|he|>",
|
| 208 |
"single_word": false,
|
| 209 |
"lstrip": false,
|
| 210 |
"rstrip": false,
|
| 211 |
+
"normalized": false
|
|
|
|
| 212 |
},
|
| 213 |
{
|
| 214 |
"id": 50280,
|
| 215 |
+
"special": true,
|
| 216 |
"content": "<|uk|>",
|
| 217 |
"single_word": false,
|
| 218 |
"lstrip": false,
|
| 219 |
"rstrip": false,
|
| 220 |
+
"normalized": false
|
|
|
|
| 221 |
},
|
| 222 |
{
|
| 223 |
"id": 50281,
|
| 224 |
+
"special": true,
|
| 225 |
"content": "<|el|>",
|
| 226 |
"single_word": false,
|
| 227 |
"lstrip": false,
|
| 228 |
"rstrip": false,
|
| 229 |
+
"normalized": false
|
|
|
|
| 230 |
},
|
| 231 |
{
|
| 232 |
"id": 50282,
|
| 233 |
+
"special": true,
|
| 234 |
"content": "<|ms|>",
|
| 235 |
"single_word": false,
|
| 236 |
"lstrip": false,
|
| 237 |
"rstrip": false,
|
| 238 |
+
"normalized": false
|
|
|
|
| 239 |
},
|
| 240 |
{
|
| 241 |
"id": 50283,
|
| 242 |
+
"special": true,
|
| 243 |
"content": "<|cs|>",
|
| 244 |
"single_word": false,
|
| 245 |
"lstrip": false,
|
| 246 |
"rstrip": false,
|
| 247 |
+
"normalized": false
|
|
|
|
| 248 |
},
|
| 249 |
{
|
| 250 |
"id": 50284,
|
| 251 |
+
"special": true,
|
| 252 |
"content": "<|ro|>",
|
| 253 |
"single_word": false,
|
| 254 |
"lstrip": false,
|
| 255 |
"rstrip": false,
|
| 256 |
+
"normalized": false
|
|
|
|
| 257 |
},
|
| 258 |
{
|
| 259 |
"id": 50285,
|
| 260 |
+
"special": true,
|
| 261 |
"content": "<|da|>",
|
| 262 |
"single_word": false,
|
| 263 |
"lstrip": false,
|
| 264 |
"rstrip": false,
|
| 265 |
+
"normalized": false
|
|
|
|
| 266 |
},
|
| 267 |
{
|
| 268 |
"id": 50286,
|
| 269 |
+
"special": true,
|
| 270 |
"content": "<|hu|>",
|
| 271 |
"single_word": false,
|
| 272 |
"lstrip": false,
|
| 273 |
"rstrip": false,
|
| 274 |
+
"normalized": false
|
|
|
|
| 275 |
},
|
| 276 |
{
|
| 277 |
"id": 50287,
|
| 278 |
+
"special": true,
|
| 279 |
"content": "<|ta|>",
|
| 280 |
"single_word": false,
|
| 281 |
"lstrip": false,
|
| 282 |
"rstrip": false,
|
| 283 |
+
"normalized": false
|
|
|
|
| 284 |
},
|
| 285 |
{
|
| 286 |
"id": 50288,
|
| 287 |
+
"special": true,
|
| 288 |
"content": "<|no|>",
|
| 289 |
"single_word": false,
|
| 290 |
"lstrip": false,
|
| 291 |
"rstrip": false,
|
| 292 |
+
"normalized": false
|
|
|
|
| 293 |
},
|
| 294 |
{
|
| 295 |
"id": 50289,
|
| 296 |
+
"special": true,
|
| 297 |
"content": "<|th|>",
|
| 298 |
"single_word": false,
|
| 299 |
"lstrip": false,
|
| 300 |
"rstrip": false,
|
| 301 |
+
"normalized": false
|
|
|
|
| 302 |
},
|
| 303 |
{
|
| 304 |
"id": 50290,
|
| 305 |
+
"special": true,
|
| 306 |
"content": "<|ur|>",
|
| 307 |
"single_word": false,
|
| 308 |
"lstrip": false,
|
| 309 |
"rstrip": false,
|
| 310 |
+
"normalized": false
|
|
|
|
| 311 |
},
|
| 312 |
{
|
| 313 |
"id": 50291,
|
| 314 |
+
"special": true,
|
| 315 |
"content": "<|hr|>",
|
| 316 |
"single_word": false,
|
| 317 |
"lstrip": false,
|
| 318 |
"rstrip": false,
|
| 319 |
+
"normalized": false
|
|
|
|
| 320 |
},
|
| 321 |
{
|
| 322 |
"id": 50292,
|
| 323 |
+
"special": true,
|
| 324 |
"content": "<|bg|>",
|
| 325 |
"single_word": false,
|
| 326 |
"lstrip": false,
|
| 327 |
"rstrip": false,
|
| 328 |
+
"normalized": false
|
|
|
|
| 329 |
},
|
| 330 |
{
|
| 331 |
"id": 50293,
|
| 332 |
+
"special": true,
|
| 333 |
"content": "<|lt|>",
|
| 334 |
"single_word": false,
|
| 335 |
"lstrip": false,
|
| 336 |
"rstrip": false,
|
| 337 |
+
"normalized": false
|
|
|
|
| 338 |
},
|
| 339 |
{
|
| 340 |
"id": 50294,
|
| 341 |
+
"special": true,
|
| 342 |
"content": "<|la|>",
|
| 343 |
"single_word": false,
|
| 344 |
"lstrip": false,
|
| 345 |
"rstrip": false,
|
| 346 |
+
"normalized": false
|
|
|
|
| 347 |
},
|
| 348 |
{
|
| 349 |
"id": 50295,
|
| 350 |
+
"special": true,
|
| 351 |
"content": "<|mi|>",
|
| 352 |
"single_word": false,
|
| 353 |
"lstrip": false,
|
| 354 |
"rstrip": false,
|
| 355 |
+
"normalized": false
|
|
|
|
| 356 |
},
|
| 357 |
{
|
| 358 |
"id": 50296,
|
| 359 |
+
"special": true,
|
| 360 |
"content": "<|ml|>",
|
| 361 |
"single_word": false,
|
| 362 |
"lstrip": false,
|
| 363 |
"rstrip": false,
|
| 364 |
+
"normalized": false
|
|
|
|
| 365 |
},
|
| 366 |
{
|
| 367 |
"id": 50297,
|
| 368 |
+
"special": true,
|
| 369 |
"content": "<|cy|>",
|
| 370 |
"single_word": false,
|
| 371 |
"lstrip": false,
|
| 372 |
"rstrip": false,
|
| 373 |
+
"normalized": false
|
|
|
|
| 374 |
},
|
| 375 |
{
|
| 376 |
"id": 50298,
|
| 377 |
+
"special": true,
|
| 378 |
"content": "<|sk|>",
|
| 379 |
"single_word": false,
|
| 380 |
"lstrip": false,
|
| 381 |
"rstrip": false,
|
| 382 |
+
"normalized": false
|
|
|
|
| 383 |
},
|
| 384 |
{
|
| 385 |
"id": 50299,
|
| 386 |
+
"special": true,
|
| 387 |
"content": "<|te|>",
|
| 388 |
"single_word": false,
|
| 389 |
"lstrip": false,
|
| 390 |
"rstrip": false,
|
| 391 |
+
"normalized": false
|
|
|
|
| 392 |
},
|
| 393 |
{
|
| 394 |
"id": 50300,
|
| 395 |
+
"special": true,
|
| 396 |
"content": "<|fa|>",
|
| 397 |
"single_word": false,
|
| 398 |
"lstrip": false,
|
| 399 |
"rstrip": false,
|
| 400 |
+
"normalized": false
|
|
|
|
| 401 |
},
|
| 402 |
{
|
| 403 |
"id": 50301,
|
| 404 |
+
"special": true,
|
| 405 |
"content": "<|lv|>",
|
| 406 |
"single_word": false,
|
| 407 |
"lstrip": false,
|
| 408 |
"rstrip": false,
|
| 409 |
+
"normalized": false
|
|
|
|
| 410 |
},
|
| 411 |
{
|
| 412 |
"id": 50302,
|
| 413 |
+
"special": true,
|
| 414 |
"content": "<|bn|>",
|
| 415 |
"single_word": false,
|
| 416 |
"lstrip": false,
|
| 417 |
"rstrip": false,
|
| 418 |
+
"normalized": false
|
|
|
|
| 419 |
},
|
| 420 |
{
|
| 421 |
"id": 50303,
|
| 422 |
+
"special": true,
|
| 423 |
"content": "<|sr|>",
|
| 424 |
"single_word": false,
|
| 425 |
"lstrip": false,
|
| 426 |
"rstrip": false,
|
| 427 |
+
"normalized": false
|
|
|
|
| 428 |
},
|
| 429 |
{
|
| 430 |
"id": 50304,
|
| 431 |
+
"special": true,
|
| 432 |
"content": "<|az|>",
|
| 433 |
"single_word": false,
|
| 434 |
"lstrip": false,
|
| 435 |
"rstrip": false,
|
| 436 |
+
"normalized": false
|
|
|
|
| 437 |
},
|
| 438 |
{
|
| 439 |
"id": 50305,
|
| 440 |
+
"special": true,
|
| 441 |
"content": "<|sl|>",
|
| 442 |
"single_word": false,
|
| 443 |
"lstrip": false,
|
| 444 |
"rstrip": false,
|
| 445 |
+
"normalized": false
|
|
|
|
| 446 |
},
|
| 447 |
{
|
| 448 |
"id": 50306,
|
| 449 |
+
"special": true,
|
| 450 |
"content": "<|kn|>",
|
| 451 |
"single_word": false,
|
| 452 |
"lstrip": false,
|
| 453 |
"rstrip": false,
|
| 454 |
+
"normalized": false
|
|
|
|
| 455 |
},
|
| 456 |
{
|
| 457 |
"id": 50307,
|
| 458 |
+
"special": true,
|
| 459 |
"content": "<|et|>",
|
| 460 |
"single_word": false,
|
| 461 |
"lstrip": false,
|
| 462 |
"rstrip": false,
|
| 463 |
+
"normalized": false
|
|
|
|
| 464 |
},
|
| 465 |
{
|
| 466 |
"id": 50308,
|
| 467 |
+
"special": true,
|
| 468 |
"content": "<|mk|>",
|
| 469 |
"single_word": false,
|
| 470 |
"lstrip": false,
|
| 471 |
"rstrip": false,
|
| 472 |
+
"normalized": false
|
|
|
|
| 473 |
},
|
| 474 |
{
|
| 475 |
"id": 50309,
|
| 476 |
+
"special": true,
|
| 477 |
"content": "<|br|>",
|
| 478 |
"single_word": false,
|
| 479 |
"lstrip": false,
|
| 480 |
"rstrip": false,
|
| 481 |
+
"normalized": false
|
|
|
|
| 482 |
},
|
| 483 |
{
|
| 484 |
"id": 50310,
|
| 485 |
+
"special": true,
|
| 486 |
"content": "<|eu|>",
|
| 487 |
"single_word": false,
|
| 488 |
"lstrip": false,
|
| 489 |
"rstrip": false,
|
| 490 |
+
"normalized": false
|
|
|
|
| 491 |
},
|
| 492 |
{
|
| 493 |
"id": 50311,
|
| 494 |
+
"special": true,
|
| 495 |
"content": "<|is|>",
|
| 496 |
"single_word": false,
|
| 497 |
"lstrip": false,
|
| 498 |
"rstrip": false,
|
| 499 |
+
"normalized": false
|
|
|
|
| 500 |
},
|
| 501 |
{
|
| 502 |
"id": 50312,
|
| 503 |
+
"special": true,
|
| 504 |
"content": "<|hy|>",
|
| 505 |
"single_word": false,
|
| 506 |
"lstrip": false,
|
| 507 |
"rstrip": false,
|
| 508 |
+
"normalized": false
|
|
|
|
| 509 |
},
|
| 510 |
{
|
| 511 |
"id": 50313,
|
| 512 |
+
"special": true,
|
| 513 |
"content": "<|ne|>",
|
| 514 |
"single_word": false,
|
| 515 |
"lstrip": false,
|
| 516 |
"rstrip": false,
|
| 517 |
+
"normalized": false
|
|
|
|
| 518 |
},
|
| 519 |
{
|
| 520 |
"id": 50314,
|
| 521 |
+
"special": true,
|
| 522 |
"content": "<|mn|>",
|
| 523 |
"single_word": false,
|
| 524 |
"lstrip": false,
|
| 525 |
"rstrip": false,
|
| 526 |
+
"normalized": false
|
|
|
|
| 527 |
},
|
| 528 |
{
|
| 529 |
"id": 50315,
|
| 530 |
+
"special": true,
|
| 531 |
"content": "<|bs|>",
|
| 532 |
"single_word": false,
|
| 533 |
"lstrip": false,
|
| 534 |
"rstrip": false,
|
| 535 |
+
"normalized": false
|
|
|
|
| 536 |
},
|
| 537 |
{
|
| 538 |
"id": 50316,
|
| 539 |
+
"special": true,
|
| 540 |
"content": "<|kk|>",
|
| 541 |
"single_word": false,
|
| 542 |
"lstrip": false,
|
| 543 |
"rstrip": false,
|
| 544 |
+
"normalized": false
|
|
|
|
| 545 |
},
|
| 546 |
{
|
| 547 |
"id": 50317,
|
| 548 |
+
"special": true,
|
| 549 |
"content": "<|sq|>",
|
| 550 |
"single_word": false,
|
| 551 |
"lstrip": false,
|
| 552 |
"rstrip": false,
|
| 553 |
+
"normalized": false
|
|
|
|
| 554 |
},
|
| 555 |
{
|
| 556 |
"id": 50318,
|
| 557 |
+
"special": true,
|
| 558 |
"content": "<|sw|>",
|
| 559 |
"single_word": false,
|
| 560 |
"lstrip": false,
|
| 561 |
"rstrip": false,
|
| 562 |
+
"normalized": false
|
|
|
|
| 563 |
},
|
| 564 |
{
|
| 565 |
"id": 50319,
|
| 566 |
+
"special": true,
|
| 567 |
"content": "<|gl|>",
|
| 568 |
"single_word": false,
|
| 569 |
"lstrip": false,
|
| 570 |
"rstrip": false,
|
| 571 |
+
"normalized": false
|
|
|
|
| 572 |
},
|
| 573 |
{
|
| 574 |
"id": 50320,
|
| 575 |
+
"special": true,
|
| 576 |
"content": "<|mr|>",
|
| 577 |
"single_word": false,
|
| 578 |
"lstrip": false,
|
| 579 |
"rstrip": false,
|
| 580 |
+
"normalized": false
|
|
|
|
| 581 |
},
|
| 582 |
{
|
| 583 |
"id": 50321,
|
| 584 |
+
"special": true,
|
| 585 |
"content": "<|pa|>",
|
| 586 |
"single_word": false,
|
| 587 |
"lstrip": false,
|
| 588 |
"rstrip": false,
|
| 589 |
+
"normalized": false
|
|
|
|
| 590 |
},
|
| 591 |
{
|
| 592 |
"id": 50322,
|
| 593 |
+
"special": true,
|
| 594 |
"content": "<|si|>",
|
| 595 |
"single_word": false,
|
| 596 |
"lstrip": false,
|
| 597 |
"rstrip": false,
|
| 598 |
+
"normalized": false
|
|
|
|
| 599 |
},
|
| 600 |
{
|
| 601 |
"id": 50323,
|
| 602 |
+
"special": true,
|
| 603 |
"content": "<|km|>",
|
| 604 |
"single_word": false,
|
| 605 |
"lstrip": false,
|
| 606 |
"rstrip": false,
|
| 607 |
+
"normalized": false
|
|
|
|
| 608 |
},
|
| 609 |
{
|
| 610 |
"id": 50324,
|
| 611 |
+
"special": true,
|
| 612 |
"content": "<|sn|>",
|
| 613 |
"single_word": false,
|
| 614 |
"lstrip": false,
|
| 615 |
"rstrip": false,
|
| 616 |
+
"normalized": false
|
|
|
|
| 617 |
},
|
| 618 |
{
|
| 619 |
"id": 50325,
|
| 620 |
+
"special": true,
|
| 621 |
"content": "<|yo|>",
|
| 622 |
"single_word": false,
|
| 623 |
"lstrip": false,
|
| 624 |
"rstrip": false,
|
| 625 |
+
"normalized": false
|
|
|
|
| 626 |
},
|
| 627 |
{
|
| 628 |
"id": 50326,
|
| 629 |
+
"special": true,
|
| 630 |
"content": "<|so|>",
|
| 631 |
"single_word": false,
|
| 632 |
"lstrip": false,
|
| 633 |
"rstrip": false,
|
| 634 |
+
"normalized": false
|
|
|
|
| 635 |
},
|
| 636 |
{
|
| 637 |
"id": 50327,
|
| 638 |
+
"special": true,
|
| 639 |
"content": "<|af|>",
|
| 640 |
"single_word": false,
|
| 641 |
"lstrip": false,
|
| 642 |
"rstrip": false,
|
| 643 |
+
"normalized": false
|
|
|
|
| 644 |
},
|
| 645 |
{
|
| 646 |
"id": 50328,
|
| 647 |
+
"special": true,
|
| 648 |
"content": "<|oc|>",
|
| 649 |
"single_word": false,
|
| 650 |
"lstrip": false,
|
| 651 |
"rstrip": false,
|
| 652 |
+
"normalized": false
|
|
|
|
| 653 |
},
|
| 654 |
{
|
| 655 |
"id": 50329,
|
| 656 |
+
"special": true,
|
| 657 |
"content": "<|ka|>",
|
| 658 |
"single_word": false,
|
| 659 |
"lstrip": false,
|
| 660 |
"rstrip": false,
|
| 661 |
+
"normalized": false
|
|
|
|
| 662 |
},
|
| 663 |
{
|
| 664 |
"id": 50330,
|
| 665 |
+
"special": true,
|
| 666 |
"content": "<|be|>",
|
| 667 |
"single_word": false,
|
| 668 |
"lstrip": false,
|
| 669 |
"rstrip": false,
|
| 670 |
+
"normalized": false
|
|
|
|
| 671 |
},
|
| 672 |
{
|
| 673 |
"id": 50331,
|
| 674 |
+
"special": true,
|
| 675 |
"content": "<|tg|>",
|
| 676 |
"single_word": false,
|
| 677 |
"lstrip": false,
|
| 678 |
"rstrip": false,
|
| 679 |
+
"normalized": false
|
|
|
|
| 680 |
},
|
| 681 |
{
|
| 682 |
"id": 50332,
|
| 683 |
+
"special": true,
|
| 684 |
"content": "<|sd|>",
|
| 685 |
"single_word": false,
|
| 686 |
"lstrip": false,
|
| 687 |
"rstrip": false,
|
| 688 |
+
"normalized": false
|
|
|
|
| 689 |
},
|
| 690 |
{
|
| 691 |
"id": 50333,
|
| 692 |
+
"special": true,
|
| 693 |
"content": "<|gu|>",
|
| 694 |
"single_word": false,
|
| 695 |
"lstrip": false,
|
| 696 |
"rstrip": false,
|
| 697 |
+
"normalized": false
|
|
|
|
| 698 |
},
|
| 699 |
{
|
| 700 |
"id": 50334,
|
| 701 |
+
"special": true,
|
| 702 |
"content": "<|am|>",
|
| 703 |
"single_word": false,
|
| 704 |
"lstrip": false,
|
| 705 |
"rstrip": false,
|
| 706 |
+
"normalized": false
|
|
|
|
| 707 |
},
|
| 708 |
{
|
| 709 |
"id": 50335,
|
| 710 |
+
"special": true,
|
| 711 |
"content": "<|yi|>",
|
| 712 |
"single_word": false,
|
| 713 |
"lstrip": false,
|
| 714 |
"rstrip": false,
|
| 715 |
+
"normalized": false
|
|
|
|
| 716 |
},
|
| 717 |
{
|
| 718 |
"id": 50336,
|
| 719 |
+
"special": true,
|
| 720 |
"content": "<|lo|>",
|
| 721 |
"single_word": false,
|
| 722 |
"lstrip": false,
|
| 723 |
"rstrip": false,
|
| 724 |
+
"normalized": false
|
|
|
|
| 725 |
},
|
| 726 |
{
|
| 727 |
"id": 50337,
|
| 728 |
+
"special": true,
|
| 729 |
"content": "<|uz|>",
|
| 730 |
"single_word": false,
|
| 731 |
"lstrip": false,
|
| 732 |
"rstrip": false,
|
| 733 |
+
"normalized": false
|
|
|
|
| 734 |
},
|
| 735 |
{
|
| 736 |
"id": 50338,
|
| 737 |
+
"special": true,
|
| 738 |
"content": "<|fo|>",
|
| 739 |
"single_word": false,
|
| 740 |
"lstrip": false,
|
| 741 |
"rstrip": false,
|
| 742 |
+
"normalized": false
|
|
|
|
| 743 |
},
|
| 744 |
{
|
| 745 |
"id": 50339,
|
| 746 |
+
"special": true,
|
| 747 |
"content": "<|ht|>",
|
| 748 |
"single_word": false,
|
| 749 |
"lstrip": false,
|
| 750 |
"rstrip": false,
|
| 751 |
+
"normalized": false
|
|
|
|
| 752 |
},
|
| 753 |
{
|
| 754 |
"id": 50340,
|
| 755 |
+
"special": true,
|
| 756 |
"content": "<|ps|>",
|
| 757 |
"single_word": false,
|
| 758 |
"lstrip": false,
|
| 759 |
"rstrip": false,
|
| 760 |
+
"normalized": false
|
|
|
|
| 761 |
},
|
| 762 |
{
|
| 763 |
"id": 50341,
|
| 764 |
+
"special": true,
|
| 765 |
"content": "<|tk|>",
|
| 766 |
"single_word": false,
|
| 767 |
"lstrip": false,
|
| 768 |
"rstrip": false,
|
| 769 |
+
"normalized": false
|
|
|
|
| 770 |
},
|
| 771 |
{
|
| 772 |
"id": 50342,
|
| 773 |
+
"special": true,
|
| 774 |
"content": "<|nn|>",
|
| 775 |
"single_word": false,
|
| 776 |
"lstrip": false,
|
| 777 |
"rstrip": false,
|
| 778 |
+
"normalized": false
|
|
|
|
| 779 |
},
|
| 780 |
{
|
| 781 |
"id": 50343,
|
| 782 |
+
"special": true,
|
| 783 |
"content": "<|mt|>",
|
| 784 |
"single_word": false,
|
| 785 |
"lstrip": false,
|
| 786 |
"rstrip": false,
|
| 787 |
+
"normalized": false
|
|
|
|
| 788 |
},
|
| 789 |
{
|
| 790 |
"id": 50344,
|
| 791 |
+
"special": true,
|
| 792 |
"content": "<|sa|>",
|
| 793 |
"single_word": false,
|
| 794 |
"lstrip": false,
|
| 795 |
"rstrip": false,
|
| 796 |
+
"normalized": false
|
|
|
|
| 797 |
},
|
| 798 |
{
|
| 799 |
"id": 50345,
|
| 800 |
+
"special": true,
|
| 801 |
"content": "<|lb|>",
|
| 802 |
"single_word": false,
|
| 803 |
"lstrip": false,
|
| 804 |
"rstrip": false,
|
| 805 |
+
"normalized": false
|
|
|
|
| 806 |
},
|
| 807 |
{
|
| 808 |
"id": 50346,
|
| 809 |
+
"special": true,
|
| 810 |
"content": "<|my|>",
|
| 811 |
"single_word": false,
|
| 812 |
"lstrip": false,
|
| 813 |
"rstrip": false,
|
| 814 |
+
"normalized": false
|
|
|
|
| 815 |
},
|
| 816 |
{
|
| 817 |
"id": 50347,
|
| 818 |
+
"special": true,
|
| 819 |
"content": "<|bo|>",
|
| 820 |
"single_word": false,
|
| 821 |
"lstrip": false,
|
| 822 |
"rstrip": false,
|
| 823 |
+
"normalized": false
|
|
|
|
| 824 |
},
|
| 825 |
{
|
| 826 |
"id": 50348,
|
| 827 |
+
"special": true,
|
| 828 |
"content": "<|tl|>",
|
| 829 |
"single_word": false,
|
| 830 |
"lstrip": false,
|
| 831 |
"rstrip": false,
|
| 832 |
+
"normalized": false
|
|
|
|
| 833 |
},
|
| 834 |
{
|
| 835 |
"id": 50349,
|
| 836 |
+
"special": true,
|
| 837 |
"content": "<|mg|>",
|
| 838 |
"single_word": false,
|
| 839 |
"lstrip": false,
|
| 840 |
"rstrip": false,
|
| 841 |
+
"normalized": false
|
|
|
|
| 842 |
},
|
| 843 |
{
|
| 844 |
"id": 50350,
|
| 845 |
+
"special": true,
|
| 846 |
"content": "<|as|>",
|
| 847 |
"single_word": false,
|
| 848 |
"lstrip": false,
|
| 849 |
"rstrip": false,
|
| 850 |
+
"normalized": false
|
|
|
|
| 851 |
},
|
| 852 |
{
|
| 853 |
"id": 50351,
|
| 854 |
+
"special": true,
|
| 855 |
"content": "<|tt|>",
|
| 856 |
"single_word": false,
|
| 857 |
"lstrip": false,
|
| 858 |
"rstrip": false,
|
| 859 |
+
"normalized": false
|
|
|
|
| 860 |
},
|
| 861 |
{
|
| 862 |
"id": 50352,
|
| 863 |
+
"special": true,
|
| 864 |
"content": "<|haw|>",
|
| 865 |
"single_word": false,
|
| 866 |
"lstrip": false,
|
| 867 |
"rstrip": false,
|
| 868 |
+
"normalized": false
|
|
|
|
| 869 |
},
|
| 870 |
{
|
| 871 |
"id": 50353,
|
| 872 |
+
"special": true,
|
| 873 |
"content": "<|ln|>",
|
| 874 |
"single_word": false,
|
| 875 |
"lstrip": false,
|
| 876 |
"rstrip": false,
|
| 877 |
+
"normalized": false
|
|
|
|
| 878 |
},
|
| 879 |
{
|
| 880 |
"id": 50354,
|
| 881 |
+
"special": true,
|
| 882 |
"content": "<|ha|>",
|
| 883 |
"single_word": false,
|
| 884 |
"lstrip": false,
|
| 885 |
"rstrip": false,
|
| 886 |
+
"normalized": false
|
|
|
|
| 887 |
},
|
| 888 |
{
|
| 889 |
"id": 50355,
|
| 890 |
+
"special": true,
|
| 891 |
"content": "<|ba|>",
|
| 892 |
"single_word": false,
|
| 893 |
"lstrip": false,
|
| 894 |
"rstrip": false,
|
| 895 |
+
"normalized": false
|
|
|
|
| 896 |
},
|
| 897 |
{
|
| 898 |
"id": 50356,
|
| 899 |
+
"special": true,
|
| 900 |
"content": "<|jw|>",
|
| 901 |
"single_word": false,
|
| 902 |
"lstrip": false,
|
| 903 |
"rstrip": false,
|
| 904 |
+
"normalized": false
|
|
|
|
| 905 |
},
|
| 906 |
{
|
| 907 |
"id": 50357,
|
| 908 |
+
"special": true,
|
| 909 |
"content": "<|su|>",
|
| 910 |
"single_word": false,
|
| 911 |
"lstrip": false,
|
| 912 |
"rstrip": false,
|
| 913 |
+
"normalized": false
|
|
|
|
| 914 |
},
|
| 915 |
{
|
| 916 |
"id": 50358,
|
| 917 |
+
"special": true,
|
| 918 |
"content": "<|translate|>",
|
| 919 |
"single_word": false,
|
| 920 |
"lstrip": false,
|
| 921 |
"rstrip": false,
|
| 922 |
+
"normalized": false
|
|
|
|
| 923 |
},
|
| 924 |
{
|
| 925 |
"id": 50359,
|
| 926 |
+
"special": true,
|
| 927 |
"content": "<|transcribe|>",
|
| 928 |
"single_word": false,
|
| 929 |
"lstrip": false,
|
| 930 |
"rstrip": false,
|
| 931 |
+
"normalized": false
|
|
|
|
| 932 |
},
|
| 933 |
{
|
| 934 |
"id": 50360,
|
| 935 |
+
"special": true,
|
| 936 |
"content": "<|startoflm|>",
|
| 937 |
"single_word": false,
|
| 938 |
"lstrip": false,
|
| 939 |
"rstrip": false,
|
| 940 |
+
"normalized": false
|
|
|
|
| 941 |
},
|
| 942 |
{
|
| 943 |
"id": 50361,
|
| 944 |
+
"special": true,
|
| 945 |
"content": "<|startofprev|>",
|
| 946 |
"single_word": false,
|
| 947 |
"lstrip": false,
|
| 948 |
"rstrip": false,
|
| 949 |
+
"normalized": false
|
|
|
|
| 950 |
},
|
| 951 |
{
|
| 952 |
"id": 50362,
|
| 953 |
+
"special": true,
|
| 954 |
"content": "<|nocaptions|>",
|
| 955 |
"single_word": false,
|
| 956 |
"lstrip": false,
|
| 957 |
"rstrip": false,
|
| 958 |
+
"normalized": false
|
|
|
|
| 959 |
},
|
| 960 |
{
|
| 961 |
"id": 50363,
|
| 962 |
+
"special": true,
|
| 963 |
"content": "<|notimestamps|>",
|
| 964 |
"single_word": false,
|
| 965 |
"lstrip": false,
|
| 966 |
"rstrip": false,
|
| 967 |
+
"normalized": false
|
|
|
|
| 968 |
}
|
| 969 |
],
|
| 970 |
"normalizer": null,
|
| 971 |
"pre_tokenizer": {
|
| 972 |
"type": "ByteLevel",
|
| 973 |
"add_prefix_space": false,
|
| 974 |
+
"trim_offsets": true
|
|
|
|
| 975 |
},
|
| 976 |
"post_processor": {
|
| 977 |
"type": "TemplateProcessing",
|
|
|
|
| 1066 |
"decoder": {
|
| 1067 |
"type": "ByteLevel",
|
| 1068 |
"add_prefix_space": true,
|
| 1069 |
+
"trim_offsets": true
|
|
|
|
| 1070 |
},
|
| 1071 |
"model": {
|
| 1072 |
"type": "BPE",
|
quantized/openai/whisper-base/default/tokenizer_config.json
CHANGED
|
@@ -19,7 +19,6 @@
|
|
| 19 |
},
|
| 20 |
"errors": "replace",
|
| 21 |
"model_max_length": 448,
|
| 22 |
-
"name_or_path": "openai/whisper-base",
|
| 23 |
"pad_token": null,
|
| 24 |
"processor_class": "WhisperProcessor",
|
| 25 |
"return_attention_mask": false,
|
|
|
|
| 19 |
},
|
| 20 |
"errors": "replace",
|
| 21 |
"model_max_length": 448,
|
|
|
|
| 22 |
"pad_token": null,
|
| 23 |
"processor_class": "WhisperProcessor",
|
| 24 |
"return_attention_mask": false,
|
quantized/openai/whisper-base/default/vocab.json
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
quantized/openai/whisper-base/speech2seq-lm-with-past/config.json
CHANGED
|
@@ -2,6 +2,7 @@
|
|
| 2 |
"_name_or_path": "openai/whisper-base",
|
| 3 |
"activation_dropout": 0.0,
|
| 4 |
"activation_function": "gelu",
|
|
|
|
| 5 |
"architectures": [
|
| 6 |
"WhisperForConditionalGeneration"
|
| 7 |
],
|
|
@@ -11,6 +12,7 @@
|
|
| 11 |
50257
|
| 12 |
],
|
| 13 |
"bos_token_id": 50257,
|
|
|
|
| 14 |
"d_model": 512,
|
| 15 |
"decoder_attention_heads": 8,
|
| 16 |
"decoder_ffn_dim": 2048,
|
|
@@ -39,6 +41,12 @@
|
|
| 39 |
],
|
| 40 |
"init_std": 0.02,
|
| 41 |
"is_encoder_decoder": true,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 42 |
"max_length": 448,
|
| 43 |
"max_source_positions": 1500,
|
| 44 |
"max_target_positions": 448,
|
|
@@ -135,7 +143,8 @@
|
|
| 135 |
50361,
|
| 136 |
50362
|
| 137 |
],
|
| 138 |
-
"transformers_version": "4.
|
| 139 |
"use_cache": true,
|
|
|
|
| 140 |
"vocab_size": 51865
|
| 141 |
}
|
|
|
|
| 2 |
"_name_or_path": "openai/whisper-base",
|
| 3 |
"activation_dropout": 0.0,
|
| 4 |
"activation_function": "gelu",
|
| 5 |
+
"apply_spec_augment": false,
|
| 6 |
"architectures": [
|
| 7 |
"WhisperForConditionalGeneration"
|
| 8 |
],
|
|
|
|
| 12 |
50257
|
| 13 |
],
|
| 14 |
"bos_token_id": 50257,
|
| 15 |
+
"classifier_proj_size": 256,
|
| 16 |
"d_model": 512,
|
| 17 |
"decoder_attention_heads": 8,
|
| 18 |
"decoder_ffn_dim": 2048,
|
|
|
|
| 41 |
],
|
| 42 |
"init_std": 0.02,
|
| 43 |
"is_encoder_decoder": true,
|
| 44 |
+
"mask_feature_length": 10,
|
| 45 |
+
"mask_feature_min_masks": 0,
|
| 46 |
+
"mask_feature_prob": 0.0,
|
| 47 |
+
"mask_time_length": 10,
|
| 48 |
+
"mask_time_min_masks": 2,
|
| 49 |
+
"mask_time_prob": 0.05,
|
| 50 |
"max_length": 448,
|
| 51 |
"max_source_positions": 1500,
|
| 52 |
"max_target_positions": 448,
|
|
|
|
| 143 |
50361,
|
| 144 |
50362
|
| 145 |
],
|
| 146 |
+
"transformers_version": "4.27.2",
|
| 147 |
"use_cache": true,
|
| 148 |
+
"use_weighted_layer_sum": false,
|
| 149 |
"vocab_size": 51865
|
| 150 |
}
|
quantized/openai/whisper-base/speech2seq-lm-with-past/decoder_model.onnx
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:884b84248916bf5250a668a64617810285b586683f22e841a9ba8f2220fc31c2
|
| 3 |
+
size 80282446
|
quantized/openai/whisper-base/speech2seq-lm-with-past/decoder_model_merged.onnx
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:30f3e2924bdf44a0fa980d0420b126785925bae478b382baa5812af74bf89299
|
| 3 |
+
size 80478651
|
quantized/openai/whisper-base/speech2seq-lm-with-past/decoder_with_past_model.onnx
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a168553192c8c05f3af164ea4dd4cedefe4a37cee46057d775584efeef15742d
|
| 3 |
+
size 77027677
|
quantized/openai/whisper-base/speech2seq-lm-with-past/encoder_model.onnx
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:589ca79a883dd2dfae23acd7f801df018d3ffef9ed3eaa63eecfacff6bd18a6d
|
| 3 |
+
size 23321703
|
quantized/openai/whisper-base/speech2seq-lm-with-past/merges.txt
CHANGED
|
@@ -1,4 +1,4 @@
|
|
| 1 |
-
#version: 0.2
|
| 2 |
Ġ a
|
| 3 |
Ġt h
|
| 4 |
i n
|
|
|
|
| 1 |
+
#version: 0.2 - Trained by `huggingface/tokenizers`
|
| 2 |
Ġ a
|
| 3 |
Ġt h
|
| 4 |
i n
|
quantized/openai/whisper-base/speech2seq-lm-with-past/tokenizer.json
CHANGED
|
@@ -5,974 +5,973 @@
|
|
| 5 |
"added_tokens": [
|
| 6 |
{
|
| 7 |
"id": 50257,
|
|
|
|
| 8 |
"content": "<|endoftext|>",
|
| 9 |
"single_word": false,
|
| 10 |
"lstrip": false,
|
| 11 |
"rstrip": false,
|
| 12 |
-
"normalized": false
|
| 13 |
-
"special": true
|
| 14 |
},
|
| 15 |
{
|
| 16 |
"id": 50258,
|
|
|
|
| 17 |
"content": "<|startoftranscript|>",
|
| 18 |
"single_word": false,
|
| 19 |
"lstrip": false,
|
| 20 |
"rstrip": false,
|
| 21 |
-
"normalized": false
|
| 22 |
-
"special": true
|
| 23 |
},
|
| 24 |
{
|
| 25 |
"id": 50259,
|
|
|
|
| 26 |
"content": "<|en|>",
|
| 27 |
"single_word": false,
|
| 28 |
"lstrip": false,
|
| 29 |
"rstrip": false,
|
| 30 |
-
"normalized": false
|
| 31 |
-
"special": true
|
| 32 |
},
|
| 33 |
{
|
| 34 |
"id": 50260,
|
|
|
|
| 35 |
"content": "<|zh|>",
|
| 36 |
"single_word": false,
|
| 37 |
"lstrip": false,
|
| 38 |
"rstrip": false,
|
| 39 |
-
"normalized": false
|
| 40 |
-
"special": true
|
| 41 |
},
|
| 42 |
{
|
| 43 |
"id": 50261,
|
|
|
|
| 44 |
"content": "<|de|>",
|
| 45 |
"single_word": false,
|
| 46 |
"lstrip": false,
|
| 47 |
"rstrip": false,
|
| 48 |
-
"normalized": false
|
| 49 |
-
"special": true
|
| 50 |
},
|
| 51 |
{
|
| 52 |
"id": 50262,
|
|
|
|
| 53 |
"content": "<|es|>",
|
| 54 |
"single_word": false,
|
| 55 |
"lstrip": false,
|
| 56 |
"rstrip": false,
|
| 57 |
-
"normalized": false
|
| 58 |
-
"special": true
|
| 59 |
},
|
| 60 |
{
|
| 61 |
"id": 50263,
|
|
|
|
| 62 |
"content": "<|ru|>",
|
| 63 |
"single_word": false,
|
| 64 |
"lstrip": false,
|
| 65 |
"rstrip": false,
|
| 66 |
-
"normalized": false
|
| 67 |
-
"special": true
|
| 68 |
},
|
| 69 |
{
|
| 70 |
"id": 50264,
|
|
|
|
| 71 |
"content": "<|ko|>",
|
| 72 |
"single_word": false,
|
| 73 |
"lstrip": false,
|
| 74 |
"rstrip": false,
|
| 75 |
-
"normalized": false
|
| 76 |
-
"special": true
|
| 77 |
},
|
| 78 |
{
|
| 79 |
"id": 50265,
|
|
|
|
| 80 |
"content": "<|fr|>",
|
| 81 |
"single_word": false,
|
| 82 |
"lstrip": false,
|
| 83 |
"rstrip": false,
|
| 84 |
-
"normalized": false
|
| 85 |
-
"special": true
|
| 86 |
},
|
| 87 |
{
|
| 88 |
"id": 50266,
|
|
|
|
| 89 |
"content": "<|ja|>",
|
| 90 |
"single_word": false,
|
| 91 |
"lstrip": false,
|
| 92 |
"rstrip": false,
|
| 93 |
-
"normalized": false
|
| 94 |
-
"special": true
|
| 95 |
},
|
| 96 |
{
|
| 97 |
"id": 50267,
|
|
|
|
| 98 |
"content": "<|pt|>",
|
| 99 |
"single_word": false,
|
| 100 |
"lstrip": false,
|
| 101 |
"rstrip": false,
|
| 102 |
-
"normalized": false
|
| 103 |
-
"special": true
|
| 104 |
},
|
| 105 |
{
|
| 106 |
"id": 50268,
|
|
|
|
| 107 |
"content": "<|tr|>",
|
| 108 |
"single_word": false,
|
| 109 |
"lstrip": false,
|
| 110 |
"rstrip": false,
|
| 111 |
-
"normalized": false
|
| 112 |
-
"special": true
|
| 113 |
},
|
| 114 |
{
|
| 115 |
"id": 50269,
|
|
|
|
| 116 |
"content": "<|pl|>",
|
| 117 |
"single_word": false,
|
| 118 |
"lstrip": false,
|
| 119 |
"rstrip": false,
|
| 120 |
-
"normalized": false
|
| 121 |
-
"special": true
|
| 122 |
},
|
| 123 |
{
|
| 124 |
"id": 50270,
|
|
|
|
| 125 |
"content": "<|ca|>",
|
| 126 |
"single_word": false,
|
| 127 |
"lstrip": false,
|
| 128 |
"rstrip": false,
|
| 129 |
-
"normalized": false
|
| 130 |
-
"special": true
|
| 131 |
},
|
| 132 |
{
|
| 133 |
"id": 50271,
|
|
|
|
| 134 |
"content": "<|nl|>",
|
| 135 |
"single_word": false,
|
| 136 |
"lstrip": false,
|
| 137 |
"rstrip": false,
|
| 138 |
-
"normalized": false
|
| 139 |
-
"special": true
|
| 140 |
},
|
| 141 |
{
|
| 142 |
"id": 50272,
|
|
|
|
| 143 |
"content": "<|ar|>",
|
| 144 |
"single_word": false,
|
| 145 |
"lstrip": false,
|
| 146 |
"rstrip": false,
|
| 147 |
-
"normalized": false
|
| 148 |
-
"special": true
|
| 149 |
},
|
| 150 |
{
|
| 151 |
"id": 50273,
|
|
|
|
| 152 |
"content": "<|sv|>",
|
| 153 |
"single_word": false,
|
| 154 |
"lstrip": false,
|
| 155 |
"rstrip": false,
|
| 156 |
-
"normalized": false
|
| 157 |
-
"special": true
|
| 158 |
},
|
| 159 |
{
|
| 160 |
"id": 50274,
|
|
|
|
| 161 |
"content": "<|it|>",
|
| 162 |
"single_word": false,
|
| 163 |
"lstrip": false,
|
| 164 |
"rstrip": false,
|
| 165 |
-
"normalized": false
|
| 166 |
-
"special": true
|
| 167 |
},
|
| 168 |
{
|
| 169 |
"id": 50275,
|
|
|
|
| 170 |
"content": "<|id|>",
|
| 171 |
"single_word": false,
|
| 172 |
"lstrip": false,
|
| 173 |
"rstrip": false,
|
| 174 |
-
"normalized": false
|
| 175 |
-
"special": true
|
| 176 |
},
|
| 177 |
{
|
| 178 |
"id": 50276,
|
|
|
|
| 179 |
"content": "<|hi|>",
|
| 180 |
"single_word": false,
|
| 181 |
"lstrip": false,
|
| 182 |
"rstrip": false,
|
| 183 |
-
"normalized": false
|
| 184 |
-
"special": true
|
| 185 |
},
|
| 186 |
{
|
| 187 |
"id": 50277,
|
|
|
|
| 188 |
"content": "<|fi|>",
|
| 189 |
"single_word": false,
|
| 190 |
"lstrip": false,
|
| 191 |
"rstrip": false,
|
| 192 |
-
"normalized": false
|
| 193 |
-
"special": true
|
| 194 |
},
|
| 195 |
{
|
| 196 |
"id": 50278,
|
|
|
|
| 197 |
"content": "<|vi|>",
|
| 198 |
"single_word": false,
|
| 199 |
"lstrip": false,
|
| 200 |
"rstrip": false,
|
| 201 |
-
"normalized": false
|
| 202 |
-
"special": true
|
| 203 |
},
|
| 204 |
{
|
| 205 |
"id": 50279,
|
|
|
|
| 206 |
"content": "<|he|>",
|
| 207 |
"single_word": false,
|
| 208 |
"lstrip": false,
|
| 209 |
"rstrip": false,
|
| 210 |
-
"normalized": false
|
| 211 |
-
"special": true
|
| 212 |
},
|
| 213 |
{
|
| 214 |
"id": 50280,
|
|
|
|
| 215 |
"content": "<|uk|>",
|
| 216 |
"single_word": false,
|
| 217 |
"lstrip": false,
|
| 218 |
"rstrip": false,
|
| 219 |
-
"normalized": false
|
| 220 |
-
"special": true
|
| 221 |
},
|
| 222 |
{
|
| 223 |
"id": 50281,
|
|
|
|
| 224 |
"content": "<|el|>",
|
| 225 |
"single_word": false,
|
| 226 |
"lstrip": false,
|
| 227 |
"rstrip": false,
|
| 228 |
-
"normalized": false
|
| 229 |
-
"special": true
|
| 230 |
},
|
| 231 |
{
|
| 232 |
"id": 50282,
|
|
|
|
| 233 |
"content": "<|ms|>",
|
| 234 |
"single_word": false,
|
| 235 |
"lstrip": false,
|
| 236 |
"rstrip": false,
|
| 237 |
-
"normalized": false
|
| 238 |
-
"special": true
|
| 239 |
},
|
| 240 |
{
|
| 241 |
"id": 50283,
|
|
|
|
| 242 |
"content": "<|cs|>",
|
| 243 |
"single_word": false,
|
| 244 |
"lstrip": false,
|
| 245 |
"rstrip": false,
|
| 246 |
-
"normalized": false
|
| 247 |
-
"special": true
|
| 248 |
},
|
| 249 |
{
|
| 250 |
"id": 50284,
|
|
|
|
| 251 |
"content": "<|ro|>",
|
| 252 |
"single_word": false,
|
| 253 |
"lstrip": false,
|
| 254 |
"rstrip": false,
|
| 255 |
-
"normalized": false
|
| 256 |
-
"special": true
|
| 257 |
},
|
| 258 |
{
|
| 259 |
"id": 50285,
|
|
|
|
| 260 |
"content": "<|da|>",
|
| 261 |
"single_word": false,
|
| 262 |
"lstrip": false,
|
| 263 |
"rstrip": false,
|
| 264 |
-
"normalized": false
|
| 265 |
-
"special": true
|
| 266 |
},
|
| 267 |
{
|
| 268 |
"id": 50286,
|
|
|
|
| 269 |
"content": "<|hu|>",
|
| 270 |
"single_word": false,
|
| 271 |
"lstrip": false,
|
| 272 |
"rstrip": false,
|
| 273 |
-
"normalized": false
|
| 274 |
-
"special": true
|
| 275 |
},
|
| 276 |
{
|
| 277 |
"id": 50287,
|
|
|
|
| 278 |
"content": "<|ta|>",
|
| 279 |
"single_word": false,
|
| 280 |
"lstrip": false,
|
| 281 |
"rstrip": false,
|
| 282 |
-
"normalized": false
|
| 283 |
-
"special": true
|
| 284 |
},
|
| 285 |
{
|
| 286 |
"id": 50288,
|
|
|
|
| 287 |
"content": "<|no|>",
|
| 288 |
"single_word": false,
|
| 289 |
"lstrip": false,
|
| 290 |
"rstrip": false,
|
| 291 |
-
"normalized": false
|
| 292 |
-
"special": true
|
| 293 |
},
|
| 294 |
{
|
| 295 |
"id": 50289,
|
|
|
|
| 296 |
"content": "<|th|>",
|
| 297 |
"single_word": false,
|
| 298 |
"lstrip": false,
|
| 299 |
"rstrip": false,
|
| 300 |
-
"normalized": false
|
| 301 |
-
"special": true
|
| 302 |
},
|
| 303 |
{
|
| 304 |
"id": 50290,
|
|
|
|
| 305 |
"content": "<|ur|>",
|
| 306 |
"single_word": false,
|
| 307 |
"lstrip": false,
|
| 308 |
"rstrip": false,
|
| 309 |
-
"normalized": false
|
| 310 |
-
"special": true
|
| 311 |
},
|
| 312 |
{
|
| 313 |
"id": 50291,
|
|
|
|
| 314 |
"content": "<|hr|>",
|
| 315 |
"single_word": false,
|
| 316 |
"lstrip": false,
|
| 317 |
"rstrip": false,
|
| 318 |
-
"normalized": false
|
| 319 |
-
"special": true
|
| 320 |
},
|
| 321 |
{
|
| 322 |
"id": 50292,
|
|
|
|
| 323 |
"content": "<|bg|>",
|
| 324 |
"single_word": false,
|
| 325 |
"lstrip": false,
|
| 326 |
"rstrip": false,
|
| 327 |
-
"normalized": false
|
| 328 |
-
"special": true
|
| 329 |
},
|
| 330 |
{
|
| 331 |
"id": 50293,
|
|
|
|
| 332 |
"content": "<|lt|>",
|
| 333 |
"single_word": false,
|
| 334 |
"lstrip": false,
|
| 335 |
"rstrip": false,
|
| 336 |
-
"normalized": false
|
| 337 |
-
"special": true
|
| 338 |
},
|
| 339 |
{
|
| 340 |
"id": 50294,
|
|
|
|
| 341 |
"content": "<|la|>",
|
| 342 |
"single_word": false,
|
| 343 |
"lstrip": false,
|
| 344 |
"rstrip": false,
|
| 345 |
-
"normalized": false
|
| 346 |
-
"special": true
|
| 347 |
},
|
| 348 |
{
|
| 349 |
"id": 50295,
|
|
|
|
| 350 |
"content": "<|mi|>",
|
| 351 |
"single_word": false,
|
| 352 |
"lstrip": false,
|
| 353 |
"rstrip": false,
|
| 354 |
-
"normalized": false
|
| 355 |
-
"special": true
|
| 356 |
},
|
| 357 |
{
|
| 358 |
"id": 50296,
|
|
|
|
| 359 |
"content": "<|ml|>",
|
| 360 |
"single_word": false,
|
| 361 |
"lstrip": false,
|
| 362 |
"rstrip": false,
|
| 363 |
-
"normalized": false
|
| 364 |
-
"special": true
|
| 365 |
},
|
| 366 |
{
|
| 367 |
"id": 50297,
|
|
|
|
| 368 |
"content": "<|cy|>",
|
| 369 |
"single_word": false,
|
| 370 |
"lstrip": false,
|
| 371 |
"rstrip": false,
|
| 372 |
-
"normalized": false
|
| 373 |
-
"special": true
|
| 374 |
},
|
| 375 |
{
|
| 376 |
"id": 50298,
|
|
|
|
| 377 |
"content": "<|sk|>",
|
| 378 |
"single_word": false,
|
| 379 |
"lstrip": false,
|
| 380 |
"rstrip": false,
|
| 381 |
-
"normalized": false
|
| 382 |
-
"special": true
|
| 383 |
},
|
| 384 |
{
|
| 385 |
"id": 50299,
|
|
|
|
| 386 |
"content": "<|te|>",
|
| 387 |
"single_word": false,
|
| 388 |
"lstrip": false,
|
| 389 |
"rstrip": false,
|
| 390 |
-
"normalized": false
|
| 391 |
-
"special": true
|
| 392 |
},
|
| 393 |
{
|
| 394 |
"id": 50300,
|
|
|
|
| 395 |
"content": "<|fa|>",
|
| 396 |
"single_word": false,
|
| 397 |
"lstrip": false,
|
| 398 |
"rstrip": false,
|
| 399 |
-
"normalized": false
|
| 400 |
-
"special": true
|
| 401 |
},
|
| 402 |
{
|
| 403 |
"id": 50301,
|
|
|
|
| 404 |
"content": "<|lv|>",
|
| 405 |
"single_word": false,
|
| 406 |
"lstrip": false,
|
| 407 |
"rstrip": false,
|
| 408 |
-
"normalized": false
|
| 409 |
-
"special": true
|
| 410 |
},
|
| 411 |
{
|
| 412 |
"id": 50302,
|
|
|
|
| 413 |
"content": "<|bn|>",
|
| 414 |
"single_word": false,
|
| 415 |
"lstrip": false,
|
| 416 |
"rstrip": false,
|
| 417 |
-
"normalized": false
|
| 418 |
-
"special": true
|
| 419 |
},
|
| 420 |
{
|
| 421 |
"id": 50303,
|
|
|
|
| 422 |
"content": "<|sr|>",
|
| 423 |
"single_word": false,
|
| 424 |
"lstrip": false,
|
| 425 |
"rstrip": false,
|
| 426 |
-
"normalized": false
|
| 427 |
-
"special": true
|
| 428 |
},
|
| 429 |
{
|
| 430 |
"id": 50304,
|
|
|
|
| 431 |
"content": "<|az|>",
|
| 432 |
"single_word": false,
|
| 433 |
"lstrip": false,
|
| 434 |
"rstrip": false,
|
| 435 |
-
"normalized": false
|
| 436 |
-
"special": true
|
| 437 |
},
|
| 438 |
{
|
| 439 |
"id": 50305,
|
|
|
|
| 440 |
"content": "<|sl|>",
|
| 441 |
"single_word": false,
|
| 442 |
"lstrip": false,
|
| 443 |
"rstrip": false,
|
| 444 |
-
"normalized": false
|
| 445 |
-
"special": true
|
| 446 |
},
|
| 447 |
{
|
| 448 |
"id": 50306,
|
|
|
|
| 449 |
"content": "<|kn|>",
|
| 450 |
"single_word": false,
|
| 451 |
"lstrip": false,
|
| 452 |
"rstrip": false,
|
| 453 |
-
"normalized": false
|
| 454 |
-
"special": true
|
| 455 |
},
|
| 456 |
{
|
| 457 |
"id": 50307,
|
|
|
|
| 458 |
"content": "<|et|>",
|
| 459 |
"single_word": false,
|
| 460 |
"lstrip": false,
|
| 461 |
"rstrip": false,
|
| 462 |
-
"normalized": false
|
| 463 |
-
"special": true
|
| 464 |
},
|
| 465 |
{
|
| 466 |
"id": 50308,
|
|
|
|
| 467 |
"content": "<|mk|>",
|
| 468 |
"single_word": false,
|
| 469 |
"lstrip": false,
|
| 470 |
"rstrip": false,
|
| 471 |
-
"normalized": false
|
| 472 |
-
"special": true
|
| 473 |
},
|
| 474 |
{
|
| 475 |
"id": 50309,
|
|
|
|
| 476 |
"content": "<|br|>",
|
| 477 |
"single_word": false,
|
| 478 |
"lstrip": false,
|
| 479 |
"rstrip": false,
|
| 480 |
-
"normalized": false
|
| 481 |
-
"special": true
|
| 482 |
},
|
| 483 |
{
|
| 484 |
"id": 50310,
|
|
|
|
| 485 |
"content": "<|eu|>",
|
| 486 |
"single_word": false,
|
| 487 |
"lstrip": false,
|
| 488 |
"rstrip": false,
|
| 489 |
-
"normalized": false
|
| 490 |
-
"special": true
|
| 491 |
},
|
| 492 |
{
|
| 493 |
"id": 50311,
|
|
|
|
| 494 |
"content": "<|is|>",
|
| 495 |
"single_word": false,
|
| 496 |
"lstrip": false,
|
| 497 |
"rstrip": false,
|
| 498 |
-
"normalized": false
|
| 499 |
-
"special": true
|
| 500 |
},
|
| 501 |
{
|
| 502 |
"id": 50312,
|
|
|
|
| 503 |
"content": "<|hy|>",
|
| 504 |
"single_word": false,
|
| 505 |
"lstrip": false,
|
| 506 |
"rstrip": false,
|
| 507 |
-
"normalized": false
|
| 508 |
-
"special": true
|
| 509 |
},
|
| 510 |
{
|
| 511 |
"id": 50313,
|
|
|
|
| 512 |
"content": "<|ne|>",
|
| 513 |
"single_word": false,
|
| 514 |
"lstrip": false,
|
| 515 |
"rstrip": false,
|
| 516 |
-
"normalized": false
|
| 517 |
-
"special": true
|
| 518 |
},
|
| 519 |
{
|
| 520 |
"id": 50314,
|
|
|
|
| 521 |
"content": "<|mn|>",
|
| 522 |
"single_word": false,
|
| 523 |
"lstrip": false,
|
| 524 |
"rstrip": false,
|
| 525 |
-
"normalized": false
|
| 526 |
-
"special": true
|
| 527 |
},
|
| 528 |
{
|
| 529 |
"id": 50315,
|
|
|
|
| 530 |
"content": "<|bs|>",
|
| 531 |
"single_word": false,
|
| 532 |
"lstrip": false,
|
| 533 |
"rstrip": false,
|
| 534 |
-
"normalized": false
|
| 535 |
-
"special": true
|
| 536 |
},
|
| 537 |
{
|
| 538 |
"id": 50316,
|
|
|
|
| 539 |
"content": "<|kk|>",
|
| 540 |
"single_word": false,
|
| 541 |
"lstrip": false,
|
| 542 |
"rstrip": false,
|
| 543 |
-
"normalized": false
|
| 544 |
-
"special": true
|
| 545 |
},
|
| 546 |
{
|
| 547 |
"id": 50317,
|
|
|
|
| 548 |
"content": "<|sq|>",
|
| 549 |
"single_word": false,
|
| 550 |
"lstrip": false,
|
| 551 |
"rstrip": false,
|
| 552 |
-
"normalized": false
|
| 553 |
-
"special": true
|
| 554 |
},
|
| 555 |
{
|
| 556 |
"id": 50318,
|
|
|
|
| 557 |
"content": "<|sw|>",
|
| 558 |
"single_word": false,
|
| 559 |
"lstrip": false,
|
| 560 |
"rstrip": false,
|
| 561 |
-
"normalized": false
|
| 562 |
-
"special": true
|
| 563 |
},
|
| 564 |
{
|
| 565 |
"id": 50319,
|
|
|
|
| 566 |
"content": "<|gl|>",
|
| 567 |
"single_word": false,
|
| 568 |
"lstrip": false,
|
| 569 |
"rstrip": false,
|
| 570 |
-
"normalized": false
|
| 571 |
-
"special": true
|
| 572 |
},
|
| 573 |
{
|
| 574 |
"id": 50320,
|
|
|
|
| 575 |
"content": "<|mr|>",
|
| 576 |
"single_word": false,
|
| 577 |
"lstrip": false,
|
| 578 |
"rstrip": false,
|
| 579 |
-
"normalized": false
|
| 580 |
-
"special": true
|
| 581 |
},
|
| 582 |
{
|
| 583 |
"id": 50321,
|
|
|
|
| 584 |
"content": "<|pa|>",
|
| 585 |
"single_word": false,
|
| 586 |
"lstrip": false,
|
| 587 |
"rstrip": false,
|
| 588 |
-
"normalized": false
|
| 589 |
-
"special": true
|
| 590 |
},
|
| 591 |
{
|
| 592 |
"id": 50322,
|
|
|
|
| 593 |
"content": "<|si|>",
|
| 594 |
"single_word": false,
|
| 595 |
"lstrip": false,
|
| 596 |
"rstrip": false,
|
| 597 |
-
"normalized": false
|
| 598 |
-
"special": true
|
| 599 |
},
|
| 600 |
{
|
| 601 |
"id": 50323,
|
|
|
|
| 602 |
"content": "<|km|>",
|
| 603 |
"single_word": false,
|
| 604 |
"lstrip": false,
|
| 605 |
"rstrip": false,
|
| 606 |
-
"normalized": false
|
| 607 |
-
"special": true
|
| 608 |
},
|
| 609 |
{
|
| 610 |
"id": 50324,
|
|
|
|
| 611 |
"content": "<|sn|>",
|
| 612 |
"single_word": false,
|
| 613 |
"lstrip": false,
|
| 614 |
"rstrip": false,
|
| 615 |
-
"normalized": false
|
| 616 |
-
"special": true
|
| 617 |
},
|
| 618 |
{
|
| 619 |
"id": 50325,
|
|
|
|
| 620 |
"content": "<|yo|>",
|
| 621 |
"single_word": false,
|
| 622 |
"lstrip": false,
|
| 623 |
"rstrip": false,
|
| 624 |
-
"normalized": false
|
| 625 |
-
"special": true
|
| 626 |
},
|
| 627 |
{
|
| 628 |
"id": 50326,
|
|
|
|
| 629 |
"content": "<|so|>",
|
| 630 |
"single_word": false,
|
| 631 |
"lstrip": false,
|
| 632 |
"rstrip": false,
|
| 633 |
-
"normalized": false
|
| 634 |
-
"special": true
|
| 635 |
},
|
| 636 |
{
|
| 637 |
"id": 50327,
|
|
|
|
| 638 |
"content": "<|af|>",
|
| 639 |
"single_word": false,
|
| 640 |
"lstrip": false,
|
| 641 |
"rstrip": false,
|
| 642 |
-
"normalized": false
|
| 643 |
-
"special": true
|
| 644 |
},
|
| 645 |
{
|
| 646 |
"id": 50328,
|
|
|
|
| 647 |
"content": "<|oc|>",
|
| 648 |
"single_word": false,
|
| 649 |
"lstrip": false,
|
| 650 |
"rstrip": false,
|
| 651 |
-
"normalized": false
|
| 652 |
-
"special": true
|
| 653 |
},
|
| 654 |
{
|
| 655 |
"id": 50329,
|
|
|
|
| 656 |
"content": "<|ka|>",
|
| 657 |
"single_word": false,
|
| 658 |
"lstrip": false,
|
| 659 |
"rstrip": false,
|
| 660 |
-
"normalized": false
|
| 661 |
-
"special": true
|
| 662 |
},
|
| 663 |
{
|
| 664 |
"id": 50330,
|
|
|
|
| 665 |
"content": "<|be|>",
|
| 666 |
"single_word": false,
|
| 667 |
"lstrip": false,
|
| 668 |
"rstrip": false,
|
| 669 |
-
"normalized": false
|
| 670 |
-
"special": true
|
| 671 |
},
|
| 672 |
{
|
| 673 |
"id": 50331,
|
|
|
|
| 674 |
"content": "<|tg|>",
|
| 675 |
"single_word": false,
|
| 676 |
"lstrip": false,
|
| 677 |
"rstrip": false,
|
| 678 |
-
"normalized": false
|
| 679 |
-
"special": true
|
| 680 |
},
|
| 681 |
{
|
| 682 |
"id": 50332,
|
|
|
|
| 683 |
"content": "<|sd|>",
|
| 684 |
"single_word": false,
|
| 685 |
"lstrip": false,
|
| 686 |
"rstrip": false,
|
| 687 |
-
"normalized": false
|
| 688 |
-
"special": true
|
| 689 |
},
|
| 690 |
{
|
| 691 |
"id": 50333,
|
|
|
|
| 692 |
"content": "<|gu|>",
|
| 693 |
"single_word": false,
|
| 694 |
"lstrip": false,
|
| 695 |
"rstrip": false,
|
| 696 |
-
"normalized": false
|
| 697 |
-
"special": true
|
| 698 |
},
|
| 699 |
{
|
| 700 |
"id": 50334,
|
|
|
|
| 701 |
"content": "<|am|>",
|
| 702 |
"single_word": false,
|
| 703 |
"lstrip": false,
|
| 704 |
"rstrip": false,
|
| 705 |
-
"normalized": false
|
| 706 |
-
"special": true
|
| 707 |
},
|
| 708 |
{
|
| 709 |
"id": 50335,
|
|
|
|
| 710 |
"content": "<|yi|>",
|
| 711 |
"single_word": false,
|
| 712 |
"lstrip": false,
|
| 713 |
"rstrip": false,
|
| 714 |
-
"normalized": false
|
| 715 |
-
"special": true
|
| 716 |
},
|
| 717 |
{
|
| 718 |
"id": 50336,
|
|
|
|
| 719 |
"content": "<|lo|>",
|
| 720 |
"single_word": false,
|
| 721 |
"lstrip": false,
|
| 722 |
"rstrip": false,
|
| 723 |
-
"normalized": false
|
| 724 |
-
"special": true
|
| 725 |
},
|
| 726 |
{
|
| 727 |
"id": 50337,
|
|
|
|
| 728 |
"content": "<|uz|>",
|
| 729 |
"single_word": false,
|
| 730 |
"lstrip": false,
|
| 731 |
"rstrip": false,
|
| 732 |
-
"normalized": false
|
| 733 |
-
"special": true
|
| 734 |
},
|
| 735 |
{
|
| 736 |
"id": 50338,
|
|
|
|
| 737 |
"content": "<|fo|>",
|
| 738 |
"single_word": false,
|
| 739 |
"lstrip": false,
|
| 740 |
"rstrip": false,
|
| 741 |
-
"normalized": false
|
| 742 |
-
"special": true
|
| 743 |
},
|
| 744 |
{
|
| 745 |
"id": 50339,
|
|
|
|
| 746 |
"content": "<|ht|>",
|
| 747 |
"single_word": false,
|
| 748 |
"lstrip": false,
|
| 749 |
"rstrip": false,
|
| 750 |
-
"normalized": false
|
| 751 |
-
"special": true
|
| 752 |
},
|
| 753 |
{
|
| 754 |
"id": 50340,
|
|
|
|
| 755 |
"content": "<|ps|>",
|
| 756 |
"single_word": false,
|
| 757 |
"lstrip": false,
|
| 758 |
"rstrip": false,
|
| 759 |
-
"normalized": false
|
| 760 |
-
"special": true
|
| 761 |
},
|
| 762 |
{
|
| 763 |
"id": 50341,
|
|
|
|
| 764 |
"content": "<|tk|>",
|
| 765 |
"single_word": false,
|
| 766 |
"lstrip": false,
|
| 767 |
"rstrip": false,
|
| 768 |
-
"normalized": false
|
| 769 |
-
"special": true
|
| 770 |
},
|
| 771 |
{
|
| 772 |
"id": 50342,
|
|
|
|
| 773 |
"content": "<|nn|>",
|
| 774 |
"single_word": false,
|
| 775 |
"lstrip": false,
|
| 776 |
"rstrip": false,
|
| 777 |
-
"normalized": false
|
| 778 |
-
"special": true
|
| 779 |
},
|
| 780 |
{
|
| 781 |
"id": 50343,
|
|
|
|
| 782 |
"content": "<|mt|>",
|
| 783 |
"single_word": false,
|
| 784 |
"lstrip": false,
|
| 785 |
"rstrip": false,
|
| 786 |
-
"normalized": false
|
| 787 |
-
"special": true
|
| 788 |
},
|
| 789 |
{
|
| 790 |
"id": 50344,
|
|
|
|
| 791 |
"content": "<|sa|>",
|
| 792 |
"single_word": false,
|
| 793 |
"lstrip": false,
|
| 794 |
"rstrip": false,
|
| 795 |
-
"normalized": false
|
| 796 |
-
"special": true
|
| 797 |
},
|
| 798 |
{
|
| 799 |
"id": 50345,
|
|
|
|
| 800 |
"content": "<|lb|>",
|
| 801 |
"single_word": false,
|
| 802 |
"lstrip": false,
|
| 803 |
"rstrip": false,
|
| 804 |
-
"normalized": false
|
| 805 |
-
"special": true
|
| 806 |
},
|
| 807 |
{
|
| 808 |
"id": 50346,
|
|
|
|
| 809 |
"content": "<|my|>",
|
| 810 |
"single_word": false,
|
| 811 |
"lstrip": false,
|
| 812 |
"rstrip": false,
|
| 813 |
-
"normalized": false
|
| 814 |
-
"special": true
|
| 815 |
},
|
| 816 |
{
|
| 817 |
"id": 50347,
|
|
|
|
| 818 |
"content": "<|bo|>",
|
| 819 |
"single_word": false,
|
| 820 |
"lstrip": false,
|
| 821 |
"rstrip": false,
|
| 822 |
-
"normalized": false
|
| 823 |
-
"special": true
|
| 824 |
},
|
| 825 |
{
|
| 826 |
"id": 50348,
|
|
|
|
| 827 |
"content": "<|tl|>",
|
| 828 |
"single_word": false,
|
| 829 |
"lstrip": false,
|
| 830 |
"rstrip": false,
|
| 831 |
-
"normalized": false
|
| 832 |
-
"special": true
|
| 833 |
},
|
| 834 |
{
|
| 835 |
"id": 50349,
|
|
|
|
| 836 |
"content": "<|mg|>",
|
| 837 |
"single_word": false,
|
| 838 |
"lstrip": false,
|
| 839 |
"rstrip": false,
|
| 840 |
-
"normalized": false
|
| 841 |
-
"special": true
|
| 842 |
},
|
| 843 |
{
|
| 844 |
"id": 50350,
|
|
|
|
| 845 |
"content": "<|as|>",
|
| 846 |
"single_word": false,
|
| 847 |
"lstrip": false,
|
| 848 |
"rstrip": false,
|
| 849 |
-
"normalized": false
|
| 850 |
-
"special": true
|
| 851 |
},
|
| 852 |
{
|
| 853 |
"id": 50351,
|
|
|
|
| 854 |
"content": "<|tt|>",
|
| 855 |
"single_word": false,
|
| 856 |
"lstrip": false,
|
| 857 |
"rstrip": false,
|
| 858 |
-
"normalized": false
|
| 859 |
-
"special": true
|
| 860 |
},
|
| 861 |
{
|
| 862 |
"id": 50352,
|
|
|
|
| 863 |
"content": "<|haw|>",
|
| 864 |
"single_word": false,
|
| 865 |
"lstrip": false,
|
| 866 |
"rstrip": false,
|
| 867 |
-
"normalized": false
|
| 868 |
-
"special": true
|
| 869 |
},
|
| 870 |
{
|
| 871 |
"id": 50353,
|
|
|
|
| 872 |
"content": "<|ln|>",
|
| 873 |
"single_word": false,
|
| 874 |
"lstrip": false,
|
| 875 |
"rstrip": false,
|
| 876 |
-
"normalized": false
|
| 877 |
-
"special": true
|
| 878 |
},
|
| 879 |
{
|
| 880 |
"id": 50354,
|
|
|
|
| 881 |
"content": "<|ha|>",
|
| 882 |
"single_word": false,
|
| 883 |
"lstrip": false,
|
| 884 |
"rstrip": false,
|
| 885 |
-
"normalized": false
|
| 886 |
-
"special": true
|
| 887 |
},
|
| 888 |
{
|
| 889 |
"id": 50355,
|
|
|
|
| 890 |
"content": "<|ba|>",
|
| 891 |
"single_word": false,
|
| 892 |
"lstrip": false,
|
| 893 |
"rstrip": false,
|
| 894 |
-
"normalized": false
|
| 895 |
-
"special": true
|
| 896 |
},
|
| 897 |
{
|
| 898 |
"id": 50356,
|
|
|
|
| 899 |
"content": "<|jw|>",
|
| 900 |
"single_word": false,
|
| 901 |
"lstrip": false,
|
| 902 |
"rstrip": false,
|
| 903 |
-
"normalized": false
|
| 904 |
-
"special": true
|
| 905 |
},
|
| 906 |
{
|
| 907 |
"id": 50357,
|
|
|
|
| 908 |
"content": "<|su|>",
|
| 909 |
"single_word": false,
|
| 910 |
"lstrip": false,
|
| 911 |
"rstrip": false,
|
| 912 |
-
"normalized": false
|
| 913 |
-
"special": true
|
| 914 |
},
|
| 915 |
{
|
| 916 |
"id": 50358,
|
|
|
|
| 917 |
"content": "<|translate|>",
|
| 918 |
"single_word": false,
|
| 919 |
"lstrip": false,
|
| 920 |
"rstrip": false,
|
| 921 |
-
"normalized": false
|
| 922 |
-
"special": true
|
| 923 |
},
|
| 924 |
{
|
| 925 |
"id": 50359,
|
|
|
|
| 926 |
"content": "<|transcribe|>",
|
| 927 |
"single_word": false,
|
| 928 |
"lstrip": false,
|
| 929 |
"rstrip": false,
|
| 930 |
-
"normalized": false
|
| 931 |
-
"special": true
|
| 932 |
},
|
| 933 |
{
|
| 934 |
"id": 50360,
|
|
|
|
| 935 |
"content": "<|startoflm|>",
|
| 936 |
"single_word": false,
|
| 937 |
"lstrip": false,
|
| 938 |
"rstrip": false,
|
| 939 |
-
"normalized": false
|
| 940 |
-
"special": true
|
| 941 |
},
|
| 942 |
{
|
| 943 |
"id": 50361,
|
|
|
|
| 944 |
"content": "<|startofprev|>",
|
| 945 |
"single_word": false,
|
| 946 |
"lstrip": false,
|
| 947 |
"rstrip": false,
|
| 948 |
-
"normalized": false
|
| 949 |
-
"special": true
|
| 950 |
},
|
| 951 |
{
|
| 952 |
"id": 50362,
|
|
|
|
| 953 |
"content": "<|nocaptions|>",
|
| 954 |
"single_word": false,
|
| 955 |
"lstrip": false,
|
| 956 |
"rstrip": false,
|
| 957 |
-
"normalized": false
|
| 958 |
-
"special": true
|
| 959 |
},
|
| 960 |
{
|
| 961 |
"id": 50363,
|
|
|
|
| 962 |
"content": "<|notimestamps|>",
|
| 963 |
"single_word": false,
|
| 964 |
"lstrip": false,
|
| 965 |
"rstrip": false,
|
| 966 |
-
"normalized": false
|
| 967 |
-
"special": true
|
| 968 |
}
|
| 969 |
],
|
| 970 |
"normalizer": null,
|
| 971 |
"pre_tokenizer": {
|
| 972 |
"type": "ByteLevel",
|
| 973 |
"add_prefix_space": false,
|
| 974 |
-
"trim_offsets": true
|
| 975 |
-
"use_regex": true
|
| 976 |
},
|
| 977 |
"post_processor": {
|
| 978 |
"type": "TemplateProcessing",
|
|
@@ -1067,8 +1066,7 @@
|
|
| 1067 |
"decoder": {
|
| 1068 |
"type": "ByteLevel",
|
| 1069 |
"add_prefix_space": true,
|
| 1070 |
-
"trim_offsets": true
|
| 1071 |
-
"use_regex": true
|
| 1072 |
},
|
| 1073 |
"model": {
|
| 1074 |
"type": "BPE",
|
|
|
|
| 5 |
"added_tokens": [
|
| 6 |
{
|
| 7 |
"id": 50257,
|
| 8 |
+
"special": true,
|
| 9 |
"content": "<|endoftext|>",
|
| 10 |
"single_word": false,
|
| 11 |
"lstrip": false,
|
| 12 |
"rstrip": false,
|
| 13 |
+
"normalized": false
|
|
|
|
| 14 |
},
|
| 15 |
{
|
| 16 |
"id": 50258,
|
| 17 |
+
"special": true,
|
| 18 |
"content": "<|startoftranscript|>",
|
| 19 |
"single_word": false,
|
| 20 |
"lstrip": false,
|
| 21 |
"rstrip": false,
|
| 22 |
+
"normalized": false
|
|
|
|
| 23 |
},
|
| 24 |
{
|
| 25 |
"id": 50259,
|
| 26 |
+
"special": true,
|
| 27 |
"content": "<|en|>",
|
| 28 |
"single_word": false,
|
| 29 |
"lstrip": false,
|
| 30 |
"rstrip": false,
|
| 31 |
+
"normalized": false
|
|
|
|
| 32 |
},
|
| 33 |
{
|
| 34 |
"id": 50260,
|
| 35 |
+
"special": true,
|
| 36 |
"content": "<|zh|>",
|
| 37 |
"single_word": false,
|
| 38 |
"lstrip": false,
|
| 39 |
"rstrip": false,
|
| 40 |
+
"normalized": false
|
|
|
|
| 41 |
},
|
| 42 |
{
|
| 43 |
"id": 50261,
|
| 44 |
+
"special": true,
|
| 45 |
"content": "<|de|>",
|
| 46 |
"single_word": false,
|
| 47 |
"lstrip": false,
|
| 48 |
"rstrip": false,
|
| 49 |
+
"normalized": false
|
|
|
|
| 50 |
},
|
| 51 |
{
|
| 52 |
"id": 50262,
|
| 53 |
+
"special": true,
|
| 54 |
"content": "<|es|>",
|
| 55 |
"single_word": false,
|
| 56 |
"lstrip": false,
|
| 57 |
"rstrip": false,
|
| 58 |
+
"normalized": false
|
|
|
|
| 59 |
},
|
| 60 |
{
|
| 61 |
"id": 50263,
|
| 62 |
+
"special": true,
|
| 63 |
"content": "<|ru|>",
|
| 64 |
"single_word": false,
|
| 65 |
"lstrip": false,
|
| 66 |
"rstrip": false,
|
| 67 |
+
"normalized": false
|
|
|
|
| 68 |
},
|
| 69 |
{
|
| 70 |
"id": 50264,
|
| 71 |
+
"special": true,
|
| 72 |
"content": "<|ko|>",
|
| 73 |
"single_word": false,
|
| 74 |
"lstrip": false,
|
| 75 |
"rstrip": false,
|
| 76 |
+
"normalized": false
|
|
|
|
| 77 |
},
|
| 78 |
{
|
| 79 |
"id": 50265,
|
| 80 |
+
"special": true,
|
| 81 |
"content": "<|fr|>",
|
| 82 |
"single_word": false,
|
| 83 |
"lstrip": false,
|
| 84 |
"rstrip": false,
|
| 85 |
+
"normalized": false
|
|
|
|
| 86 |
},
|
| 87 |
{
|
| 88 |
"id": 50266,
|
| 89 |
+
"special": true,
|
| 90 |
"content": "<|ja|>",
|
| 91 |
"single_word": false,
|
| 92 |
"lstrip": false,
|
| 93 |
"rstrip": false,
|
| 94 |
+
"normalized": false
|
|
|
|
| 95 |
},
|
| 96 |
{
|
| 97 |
"id": 50267,
|
| 98 |
+
"special": true,
|
| 99 |
"content": "<|pt|>",
|
| 100 |
"single_word": false,
|
| 101 |
"lstrip": false,
|
| 102 |
"rstrip": false,
|
| 103 |
+
"normalized": false
|
|
|
|
| 104 |
},
|
| 105 |
{
|
| 106 |
"id": 50268,
|
| 107 |
+
"special": true,
|
| 108 |
"content": "<|tr|>",
|
| 109 |
"single_word": false,
|
| 110 |
"lstrip": false,
|
| 111 |
"rstrip": false,
|
| 112 |
+
"normalized": false
|
|
|
|
| 113 |
},
|
| 114 |
{
|
| 115 |
"id": 50269,
|
| 116 |
+
"special": true,
|
| 117 |
"content": "<|pl|>",
|
| 118 |
"single_word": false,
|
| 119 |
"lstrip": false,
|
| 120 |
"rstrip": false,
|
| 121 |
+
"normalized": false
|
|
|
|
| 122 |
},
|
| 123 |
{
|
| 124 |
"id": 50270,
|
| 125 |
+
"special": true,
|
| 126 |
"content": "<|ca|>",
|
| 127 |
"single_word": false,
|
| 128 |
"lstrip": false,
|
| 129 |
"rstrip": false,
|
| 130 |
+
"normalized": false
|
|
|
|
| 131 |
},
|
| 132 |
{
|
| 133 |
"id": 50271,
|
| 134 |
+
"special": true,
|
| 135 |
"content": "<|nl|>",
|
| 136 |
"single_word": false,
|
| 137 |
"lstrip": false,
|
| 138 |
"rstrip": false,
|
| 139 |
+
"normalized": false
|
|
|
|
| 140 |
},
|
| 141 |
{
|
| 142 |
"id": 50272,
|
| 143 |
+
"special": true,
|
| 144 |
"content": "<|ar|>",
|
| 145 |
"single_word": false,
|
| 146 |
"lstrip": false,
|
| 147 |
"rstrip": false,
|
| 148 |
+
"normalized": false
|
|
|
|
| 149 |
},
|
| 150 |
{
|
| 151 |
"id": 50273,
|
| 152 |
+
"special": true,
|
| 153 |
"content": "<|sv|>",
|
| 154 |
"single_word": false,
|
| 155 |
"lstrip": false,
|
| 156 |
"rstrip": false,
|
| 157 |
+
"normalized": false
|
|
|
|
| 158 |
},
|
| 159 |
{
|
| 160 |
"id": 50274,
|
| 161 |
+
"special": true,
|
| 162 |
"content": "<|it|>",
|
| 163 |
"single_word": false,
|
| 164 |
"lstrip": false,
|
| 165 |
"rstrip": false,
|
| 166 |
+
"normalized": false
|
|
|
|
| 167 |
},
|
| 168 |
{
|
| 169 |
"id": 50275,
|
| 170 |
+
"special": true,
|
| 171 |
"content": "<|id|>",
|
| 172 |
"single_word": false,
|
| 173 |
"lstrip": false,
|
| 174 |
"rstrip": false,
|
| 175 |
+
"normalized": false
|
|
|
|
| 176 |
},
|
| 177 |
{
|
| 178 |
"id": 50276,
|
| 179 |
+
"special": true,
|
| 180 |
"content": "<|hi|>",
|
| 181 |
"single_word": false,
|
| 182 |
"lstrip": false,
|
| 183 |
"rstrip": false,
|
| 184 |
+
"normalized": false
|
|
|
|
| 185 |
},
|
| 186 |
{
|
| 187 |
"id": 50277,
|
| 188 |
+
"special": true,
|
| 189 |
"content": "<|fi|>",
|
| 190 |
"single_word": false,
|
| 191 |
"lstrip": false,
|
| 192 |
"rstrip": false,
|
| 193 |
+
"normalized": false
|
|
|
|
| 194 |
},
|
| 195 |
{
|
| 196 |
"id": 50278,
|
| 197 |
+
"special": true,
|
| 198 |
"content": "<|vi|>",
|
| 199 |
"single_word": false,
|
| 200 |
"lstrip": false,
|
| 201 |
"rstrip": false,
|
| 202 |
+
"normalized": false
|
|
|
|
| 203 |
},
|
| 204 |
{
|
| 205 |
"id": 50279,
|
| 206 |
+
"special": true,
|
| 207 |
"content": "<|he|>",
|
| 208 |
"single_word": false,
|
| 209 |
"lstrip": false,
|
| 210 |
"rstrip": false,
|
| 211 |
+
"normalized": false
|
|
|
|
| 212 |
},
|
| 213 |
{
|
| 214 |
"id": 50280,
|
| 215 |
+
"special": true,
|
| 216 |
"content": "<|uk|>",
|
| 217 |
"single_word": false,
|
| 218 |
"lstrip": false,
|
| 219 |
"rstrip": false,
|
| 220 |
+
"normalized": false
|
|
|
|
| 221 |
},
|
| 222 |
{
|
| 223 |
"id": 50281,
|
| 224 |
+
"special": true,
|
| 225 |
"content": "<|el|>",
|
| 226 |
"single_word": false,
|
| 227 |
"lstrip": false,
|
| 228 |
"rstrip": false,
|
| 229 |
+
"normalized": false
|
|
|
|
| 230 |
},
|
| 231 |
{
|
| 232 |
"id": 50282,
|
| 233 |
+
"special": true,
|
| 234 |
"content": "<|ms|>",
|
| 235 |
"single_word": false,
|
| 236 |
"lstrip": false,
|
| 237 |
"rstrip": false,
|
| 238 |
+
"normalized": false
|
|
|
|
| 239 |
},
|
| 240 |
{
|
| 241 |
"id": 50283,
|
| 242 |
+
"special": true,
|
| 243 |
"content": "<|cs|>",
|
| 244 |
"single_word": false,
|
| 245 |
"lstrip": false,
|
| 246 |
"rstrip": false,
|
| 247 |
+
"normalized": false
|
|
|
|
| 248 |
},
|
| 249 |
{
|
| 250 |
"id": 50284,
|
| 251 |
+
"special": true,
|
| 252 |
"content": "<|ro|>",
|
| 253 |
"single_word": false,
|
| 254 |
"lstrip": false,
|
| 255 |
"rstrip": false,
|
| 256 |
+
"normalized": false
|
|
|
|
| 257 |
},
|
| 258 |
{
|
| 259 |
"id": 50285,
|
| 260 |
+
"special": true,
|
| 261 |
"content": "<|da|>",
|
| 262 |
"single_word": false,
|
| 263 |
"lstrip": false,
|
| 264 |
"rstrip": false,
|
| 265 |
+
"normalized": false
|
|
|
|
| 266 |
},
|
| 267 |
{
|
| 268 |
"id": 50286,
|
| 269 |
+
"special": true,
|
| 270 |
"content": "<|hu|>",
|
| 271 |
"single_word": false,
|
| 272 |
"lstrip": false,
|
| 273 |
"rstrip": false,
|
| 274 |
+
"normalized": false
|
|
|
|
| 275 |
},
|
| 276 |
{
|
| 277 |
"id": 50287,
|
| 278 |
+
"special": true,
|
| 279 |
"content": "<|ta|>",
|
| 280 |
"single_word": false,
|
| 281 |
"lstrip": false,
|
| 282 |
"rstrip": false,
|
| 283 |
+
"normalized": false
|
|
|
|
| 284 |
},
|
| 285 |
{
|
| 286 |
"id": 50288,
|
| 287 |
+
"special": true,
|
| 288 |
"content": "<|no|>",
|
| 289 |
"single_word": false,
|
| 290 |
"lstrip": false,
|
| 291 |
"rstrip": false,
|
| 292 |
+
"normalized": false
|
|
|
|
| 293 |
},
|
| 294 |
{
|
| 295 |
"id": 50289,
|
| 296 |
+
"special": true,
|
| 297 |
"content": "<|th|>",
|
| 298 |
"single_word": false,
|
| 299 |
"lstrip": false,
|
| 300 |
"rstrip": false,
|
| 301 |
+
"normalized": false
|
|
|
|
| 302 |
},
|
| 303 |
{
|
| 304 |
"id": 50290,
|
| 305 |
+
"special": true,
|
| 306 |
"content": "<|ur|>",
|
| 307 |
"single_word": false,
|
| 308 |
"lstrip": false,
|
| 309 |
"rstrip": false,
|
| 310 |
+
"normalized": false
|
|
|
|
| 311 |
},
|
| 312 |
{
|
| 313 |
"id": 50291,
|
| 314 |
+
"special": true,
|
| 315 |
"content": "<|hr|>",
|
| 316 |
"single_word": false,
|
| 317 |
"lstrip": false,
|
| 318 |
"rstrip": false,
|
| 319 |
+
"normalized": false
|
|
|
|
| 320 |
},
|
| 321 |
{
|
| 322 |
"id": 50292,
|
| 323 |
+
"special": true,
|
| 324 |
"content": "<|bg|>",
|
| 325 |
"single_word": false,
|
| 326 |
"lstrip": false,
|
| 327 |
"rstrip": false,
|
| 328 |
+
"normalized": false
|
|
|
|
| 329 |
},
|
| 330 |
{
|
| 331 |
"id": 50293,
|
| 332 |
+
"special": true,
|
| 333 |
"content": "<|lt|>",
|
| 334 |
"single_word": false,
|
| 335 |
"lstrip": false,
|
| 336 |
"rstrip": false,
|
| 337 |
+
"normalized": false
|
|
|
|
| 338 |
},
|
| 339 |
{
|
| 340 |
"id": 50294,
|
| 341 |
+
"special": true,
|
| 342 |
"content": "<|la|>",
|
| 343 |
"single_word": false,
|
| 344 |
"lstrip": false,
|
| 345 |
"rstrip": false,
|
| 346 |
+
"normalized": false
|
|
|
|
| 347 |
},
|
| 348 |
{
|
| 349 |
"id": 50295,
|
| 350 |
+
"special": true,
|
| 351 |
"content": "<|mi|>",
|
| 352 |
"single_word": false,
|
| 353 |
"lstrip": false,
|
| 354 |
"rstrip": false,
|
| 355 |
+
"normalized": false
|
|
|
|
| 356 |
},
|
| 357 |
{
|
| 358 |
"id": 50296,
|
| 359 |
+
"special": true,
|
| 360 |
"content": "<|ml|>",
|
| 361 |
"single_word": false,
|
| 362 |
"lstrip": false,
|
| 363 |
"rstrip": false,
|
| 364 |
+
"normalized": false
|
|
|
|
| 365 |
},
|
| 366 |
{
|
| 367 |
"id": 50297,
|
| 368 |
+
"special": true,
|
| 369 |
"content": "<|cy|>",
|
| 370 |
"single_word": false,
|
| 371 |
"lstrip": false,
|
| 372 |
"rstrip": false,
|
| 373 |
+
"normalized": false
|
|
|
|
| 374 |
},
|
| 375 |
{
|
| 376 |
"id": 50298,
|
| 377 |
+
"special": true,
|
| 378 |
"content": "<|sk|>",
|
| 379 |
"single_word": false,
|
| 380 |
"lstrip": false,
|
| 381 |
"rstrip": false,
|
| 382 |
+
"normalized": false
|
|
|
|
| 383 |
},
|
| 384 |
{
|
| 385 |
"id": 50299,
|
| 386 |
+
"special": true,
|
| 387 |
"content": "<|te|>",
|
| 388 |
"single_word": false,
|
| 389 |
"lstrip": false,
|
| 390 |
"rstrip": false,
|
| 391 |
+
"normalized": false
|
|
|
|
| 392 |
},
|
| 393 |
{
|
| 394 |
"id": 50300,
|
| 395 |
+
"special": true,
|
| 396 |
"content": "<|fa|>",
|
| 397 |
"single_word": false,
|
| 398 |
"lstrip": false,
|
| 399 |
"rstrip": false,
|
| 400 |
+
"normalized": false
|
|
|
|
| 401 |
},
|
| 402 |
{
|
| 403 |
"id": 50301,
|
| 404 |
+
"special": true,
|
| 405 |
"content": "<|lv|>",
|
| 406 |
"single_word": false,
|
| 407 |
"lstrip": false,
|
| 408 |
"rstrip": false,
|
| 409 |
+
"normalized": false
|
|
|
|
| 410 |
},
|
| 411 |
{
|
| 412 |
"id": 50302,
|
| 413 |
+
"special": true,
|
| 414 |
"content": "<|bn|>",
|
| 415 |
"single_word": false,
|
| 416 |
"lstrip": false,
|
| 417 |
"rstrip": false,
|
| 418 |
+
"normalized": false
|
|
|
|
| 419 |
},
|
| 420 |
{
|
| 421 |
"id": 50303,
|
| 422 |
+
"special": true,
|
| 423 |
"content": "<|sr|>",
|
| 424 |
"single_word": false,
|
| 425 |
"lstrip": false,
|
| 426 |
"rstrip": false,
|
| 427 |
+
"normalized": false
|
|
|
|
| 428 |
},
|
| 429 |
{
|
| 430 |
"id": 50304,
|
| 431 |
+
"special": true,
|
| 432 |
"content": "<|az|>",
|
| 433 |
"single_word": false,
|
| 434 |
"lstrip": false,
|
| 435 |
"rstrip": false,
|
| 436 |
+
"normalized": false
|
|
|
|
| 437 |
},
|
| 438 |
{
|
| 439 |
"id": 50305,
|
| 440 |
+
"special": true,
|
| 441 |
"content": "<|sl|>",
|
| 442 |
"single_word": false,
|
| 443 |
"lstrip": false,
|
| 444 |
"rstrip": false,
|
| 445 |
+
"normalized": false
|
|
|
|
| 446 |
},
|
| 447 |
{
|
| 448 |
"id": 50306,
|
| 449 |
+
"special": true,
|
| 450 |
"content": "<|kn|>",
|
| 451 |
"single_word": false,
|
| 452 |
"lstrip": false,
|
| 453 |
"rstrip": false,
|
| 454 |
+
"normalized": false
|
|
|
|
| 455 |
},
|
| 456 |
{
|
| 457 |
"id": 50307,
|
| 458 |
+
"special": true,
|
| 459 |
"content": "<|et|>",
|
| 460 |
"single_word": false,
|
| 461 |
"lstrip": false,
|
| 462 |
"rstrip": false,
|
| 463 |
+
"normalized": false
|
|
|
|
| 464 |
},
|
| 465 |
{
|
| 466 |
"id": 50308,
|
| 467 |
+
"special": true,
|
| 468 |
"content": "<|mk|>",
|
| 469 |
"single_word": false,
|
| 470 |
"lstrip": false,
|
| 471 |
"rstrip": false,
|
| 472 |
+
"normalized": false
|
|
|
|
| 473 |
},
|
| 474 |
{
|
| 475 |
"id": 50309,
|
| 476 |
+
"special": true,
|
| 477 |
"content": "<|br|>",
|
| 478 |
"single_word": false,
|
| 479 |
"lstrip": false,
|
| 480 |
"rstrip": false,
|
| 481 |
+
"normalized": false
|
|
|
|
| 482 |
},
|
| 483 |
{
|
| 484 |
"id": 50310,
|
| 485 |
+
"special": true,
|
| 486 |
"content": "<|eu|>",
|
| 487 |
"single_word": false,
|
| 488 |
"lstrip": false,
|
| 489 |
"rstrip": false,
|
| 490 |
+
"normalized": false
|
|
|
|
| 491 |
},
|
| 492 |
{
|
| 493 |
"id": 50311,
|
| 494 |
+
"special": true,
|
| 495 |
"content": "<|is|>",
|
| 496 |
"single_word": false,
|
| 497 |
"lstrip": false,
|
| 498 |
"rstrip": false,
|
| 499 |
+
"normalized": false
|
|
|
|
| 500 |
},
|
| 501 |
{
|
| 502 |
"id": 50312,
|
| 503 |
+
"special": true,
|
| 504 |
"content": "<|hy|>",
|
| 505 |
"single_word": false,
|
| 506 |
"lstrip": false,
|
| 507 |
"rstrip": false,
|
| 508 |
+
"normalized": false
|
|
|
|
| 509 |
},
|
| 510 |
{
|
| 511 |
"id": 50313,
|
| 512 |
+
"special": true,
|
| 513 |
"content": "<|ne|>",
|
| 514 |
"single_word": false,
|
| 515 |
"lstrip": false,
|
| 516 |
"rstrip": false,
|
| 517 |
+
"normalized": false
|
|
|
|
| 518 |
},
|
| 519 |
{
|
| 520 |
"id": 50314,
|
| 521 |
+
"special": true,
|
| 522 |
"content": "<|mn|>",
|
| 523 |
"single_word": false,
|
| 524 |
"lstrip": false,
|
| 525 |
"rstrip": false,
|
| 526 |
+
"normalized": false
|
|
|
|
| 527 |
},
|
| 528 |
{
|
| 529 |
"id": 50315,
|
| 530 |
+
"special": true,
|
| 531 |
"content": "<|bs|>",
|
| 532 |
"single_word": false,
|
| 533 |
"lstrip": false,
|
| 534 |
"rstrip": false,
|
| 535 |
+
"normalized": false
|
|
|
|
| 536 |
},
|
| 537 |
{
|
| 538 |
"id": 50316,
|
| 539 |
+
"special": true,
|
| 540 |
"content": "<|kk|>",
|
| 541 |
"single_word": false,
|
| 542 |
"lstrip": false,
|
| 543 |
"rstrip": false,
|
| 544 |
+
"normalized": false
|
|
|
|
| 545 |
},
|
| 546 |
{
|
| 547 |
"id": 50317,
|
| 548 |
+
"special": true,
|
| 549 |
"content": "<|sq|>",
|
| 550 |
"single_word": false,
|
| 551 |
"lstrip": false,
|
| 552 |
"rstrip": false,
|
| 553 |
+
"normalized": false
|
|
|
|
| 554 |
},
|
| 555 |
{
|
| 556 |
"id": 50318,
|
| 557 |
+
"special": true,
|
| 558 |
"content": "<|sw|>",
|
| 559 |
"single_word": false,
|
| 560 |
"lstrip": false,
|
| 561 |
"rstrip": false,
|
| 562 |
+
"normalized": false
|
|
|
|
| 563 |
},
|
| 564 |
{
|
| 565 |
"id": 50319,
|
| 566 |
+
"special": true,
|
| 567 |
"content": "<|gl|>",
|
| 568 |
"single_word": false,
|
| 569 |
"lstrip": false,
|
| 570 |
"rstrip": false,
|
| 571 |
+
"normalized": false
|
|
|
|
| 572 |
},
|
| 573 |
{
|
| 574 |
"id": 50320,
|
| 575 |
+
"special": true,
|
| 576 |
"content": "<|mr|>",
|
| 577 |
"single_word": false,
|
| 578 |
"lstrip": false,
|
| 579 |
"rstrip": false,
|
| 580 |
+
"normalized": false
|
|
|
|
| 581 |
},
|
| 582 |
{
|
| 583 |
"id": 50321,
|
| 584 |
+
"special": true,
|
| 585 |
"content": "<|pa|>",
|
| 586 |
"single_word": false,
|
| 587 |
"lstrip": false,
|
| 588 |
"rstrip": false,
|
| 589 |
+
"normalized": false
|
|
|
|
| 590 |
},
|
| 591 |
{
|
| 592 |
"id": 50322,
|
| 593 |
+
"special": true,
|
| 594 |
"content": "<|si|>",
|
| 595 |
"single_word": false,
|
| 596 |
"lstrip": false,
|
| 597 |
"rstrip": false,
|
| 598 |
+
"normalized": false
|
|
|
|
| 599 |
},
|
| 600 |
{
|
| 601 |
"id": 50323,
|
| 602 |
+
"special": true,
|
| 603 |
"content": "<|km|>",
|
| 604 |
"single_word": false,
|
| 605 |
"lstrip": false,
|
| 606 |
"rstrip": false,
|
| 607 |
+
"normalized": false
|
|
|
|
| 608 |
},
|
| 609 |
{
|
| 610 |
"id": 50324,
|
| 611 |
+
"special": true,
|
| 612 |
"content": "<|sn|>",
|
| 613 |
"single_word": false,
|
| 614 |
"lstrip": false,
|
| 615 |
"rstrip": false,
|
| 616 |
+
"normalized": false
|
|
|
|
| 617 |
},
|
| 618 |
{
|
| 619 |
"id": 50325,
|
| 620 |
+
"special": true,
|
| 621 |
"content": "<|yo|>",
|
| 622 |
"single_word": false,
|
| 623 |
"lstrip": false,
|
| 624 |
"rstrip": false,
|
| 625 |
+
"normalized": false
|
|
|
|
| 626 |
},
|
| 627 |
{
|
| 628 |
"id": 50326,
|
| 629 |
+
"special": true,
|
| 630 |
"content": "<|so|>",
|
| 631 |
"single_word": false,
|
| 632 |
"lstrip": false,
|
| 633 |
"rstrip": false,
|
| 634 |
+
"normalized": false
|
|
|
|
| 635 |
},
|
| 636 |
{
|
| 637 |
"id": 50327,
|
| 638 |
+
"special": true,
|
| 639 |
"content": "<|af|>",
|
| 640 |
"single_word": false,
|
| 641 |
"lstrip": false,
|
| 642 |
"rstrip": false,
|
| 643 |
+
"normalized": false
|
|
|
|
| 644 |
},
|
| 645 |
{
|
| 646 |
"id": 50328,
|
| 647 |
+
"special": true,
|
| 648 |
"content": "<|oc|>",
|
| 649 |
"single_word": false,
|
| 650 |
"lstrip": false,
|
| 651 |
"rstrip": false,
|
| 652 |
+
"normalized": false
|
|
|
|
| 653 |
},
|
| 654 |
{
|
| 655 |
"id": 50329,
|
| 656 |
+
"special": true,
|
| 657 |
"content": "<|ka|>",
|
| 658 |
"single_word": false,
|
| 659 |
"lstrip": false,
|
| 660 |
"rstrip": false,
|
| 661 |
+
"normalized": false
|
|
|
|
| 662 |
},
|
| 663 |
{
|
| 664 |
"id": 50330,
|
| 665 |
+
"special": true,
|
| 666 |
"content": "<|be|>",
|
| 667 |
"single_word": false,
|
| 668 |
"lstrip": false,
|
| 669 |
"rstrip": false,
|
| 670 |
+
"normalized": false
|
|
|
|
| 671 |
},
|
| 672 |
{
|
| 673 |
"id": 50331,
|
| 674 |
+
"special": true,
|
| 675 |
"content": "<|tg|>",
|
| 676 |
"single_word": false,
|
| 677 |
"lstrip": false,
|
| 678 |
"rstrip": false,
|
| 679 |
+
"normalized": false
|
|
|
|
| 680 |
},
|
| 681 |
{
|
| 682 |
"id": 50332,
|
| 683 |
+
"special": true,
|
| 684 |
"content": "<|sd|>",
|
| 685 |
"single_word": false,
|
| 686 |
"lstrip": false,
|
| 687 |
"rstrip": false,
|
| 688 |
+
"normalized": false
|
|
|
|
| 689 |
},
|
| 690 |
{
|
| 691 |
"id": 50333,
|
| 692 |
+
"special": true,
|
| 693 |
"content": "<|gu|>",
|
| 694 |
"single_word": false,
|
| 695 |
"lstrip": false,
|
| 696 |
"rstrip": false,
|
| 697 |
+
"normalized": false
|
|
|
|
| 698 |
},
|
| 699 |
{
|
| 700 |
"id": 50334,
|
| 701 |
+
"special": true,
|
| 702 |
"content": "<|am|>",
|
| 703 |
"single_word": false,
|
| 704 |
"lstrip": false,
|
| 705 |
"rstrip": false,
|
| 706 |
+
"normalized": false
|
|
|
|
| 707 |
},
|
| 708 |
{
|
| 709 |
"id": 50335,
|
| 710 |
+
"special": true,
|
| 711 |
"content": "<|yi|>",
|
| 712 |
"single_word": false,
|
| 713 |
"lstrip": false,
|
| 714 |
"rstrip": false,
|
| 715 |
+
"normalized": false
|
|
|
|
| 716 |
},
|
| 717 |
{
|
| 718 |
"id": 50336,
|
| 719 |
+
"special": true,
|
| 720 |
"content": "<|lo|>",
|
| 721 |
"single_word": false,
|
| 722 |
"lstrip": false,
|
| 723 |
"rstrip": false,
|
| 724 |
+
"normalized": false
|
|
|
|
| 725 |
},
|
| 726 |
{
|
| 727 |
"id": 50337,
|
| 728 |
+
"special": true,
|
| 729 |
"content": "<|uz|>",
|
| 730 |
"single_word": false,
|
| 731 |
"lstrip": false,
|
| 732 |
"rstrip": false,
|
| 733 |
+
"normalized": false
|
|
|
|
| 734 |
},
|
| 735 |
{
|
| 736 |
"id": 50338,
|
| 737 |
+
"special": true,
|
| 738 |
"content": "<|fo|>",
|
| 739 |
"single_word": false,
|
| 740 |
"lstrip": false,
|
| 741 |
"rstrip": false,
|
| 742 |
+
"normalized": false
|
|
|
|
| 743 |
},
|
| 744 |
{
|
| 745 |
"id": 50339,
|
| 746 |
+
"special": true,
|
| 747 |
"content": "<|ht|>",
|
| 748 |
"single_word": false,
|
| 749 |
"lstrip": false,
|
| 750 |
"rstrip": false,
|
| 751 |
+
"normalized": false
|
|
|
|
| 752 |
},
|
| 753 |
{
|
| 754 |
"id": 50340,
|
| 755 |
+
"special": true,
|
| 756 |
"content": "<|ps|>",
|
| 757 |
"single_word": false,
|
| 758 |
"lstrip": false,
|
| 759 |
"rstrip": false,
|
| 760 |
+
"normalized": false
|
|
|
|
| 761 |
},
|
| 762 |
{
|
| 763 |
"id": 50341,
|
| 764 |
+
"special": true,
|
| 765 |
"content": "<|tk|>",
|
| 766 |
"single_word": false,
|
| 767 |
"lstrip": false,
|
| 768 |
"rstrip": false,
|
| 769 |
+
"normalized": false
|
|
|
|
| 770 |
},
|
| 771 |
{
|
| 772 |
"id": 50342,
|
| 773 |
+
"special": true,
|
| 774 |
"content": "<|nn|>",
|
| 775 |
"single_word": false,
|
| 776 |
"lstrip": false,
|
| 777 |
"rstrip": false,
|
| 778 |
+
"normalized": false
|
|
|
|
| 779 |
},
|
| 780 |
{
|
| 781 |
"id": 50343,
|
| 782 |
+
"special": true,
|
| 783 |
"content": "<|mt|>",
|
| 784 |
"single_word": false,
|
| 785 |
"lstrip": false,
|
| 786 |
"rstrip": false,
|
| 787 |
+
"normalized": false
|
|
|
|
| 788 |
},
|
| 789 |
{
|
| 790 |
"id": 50344,
|
| 791 |
+
"special": true,
|
| 792 |
"content": "<|sa|>",
|
| 793 |
"single_word": false,
|
| 794 |
"lstrip": false,
|
| 795 |
"rstrip": false,
|
| 796 |
+
"normalized": false
|
|
|
|
| 797 |
},
|
| 798 |
{
|
| 799 |
"id": 50345,
|
| 800 |
+
"special": true,
|
| 801 |
"content": "<|lb|>",
|
| 802 |
"single_word": false,
|
| 803 |
"lstrip": false,
|
| 804 |
"rstrip": false,
|
| 805 |
+
"normalized": false
|
|
|
|
| 806 |
},
|
| 807 |
{
|
| 808 |
"id": 50346,
|
| 809 |
+
"special": true,
|
| 810 |
"content": "<|my|>",
|
| 811 |
"single_word": false,
|
| 812 |
"lstrip": false,
|
| 813 |
"rstrip": false,
|
| 814 |
+
"normalized": false
|
|
|
|
| 815 |
},
|
| 816 |
{
|
| 817 |
"id": 50347,
|
| 818 |
+
"special": true,
|
| 819 |
"content": "<|bo|>",
|
| 820 |
"single_word": false,
|
| 821 |
"lstrip": false,
|
| 822 |
"rstrip": false,
|
| 823 |
+
"normalized": false
|
|
|
|
| 824 |
},
|
| 825 |
{
|
| 826 |
"id": 50348,
|
| 827 |
+
"special": true,
|
| 828 |
"content": "<|tl|>",
|
| 829 |
"single_word": false,
|
| 830 |
"lstrip": false,
|
| 831 |
"rstrip": false,
|
| 832 |
+
"normalized": false
|
|
|
|
| 833 |
},
|
| 834 |
{
|
| 835 |
"id": 50349,
|
| 836 |
+
"special": true,
|
| 837 |
"content": "<|mg|>",
|
| 838 |
"single_word": false,
|
| 839 |
"lstrip": false,
|
| 840 |
"rstrip": false,
|
| 841 |
+
"normalized": false
|
|
|
|
| 842 |
},
|
| 843 |
{
|
| 844 |
"id": 50350,
|
| 845 |
+
"special": true,
|
| 846 |
"content": "<|as|>",
|
| 847 |
"single_word": false,
|
| 848 |
"lstrip": false,
|
| 849 |
"rstrip": false,
|
| 850 |
+
"normalized": false
|
|
|
|
| 851 |
},
|
| 852 |
{
|
| 853 |
"id": 50351,
|
| 854 |
+
"special": true,
|
| 855 |
"content": "<|tt|>",
|
| 856 |
"single_word": false,
|
| 857 |
"lstrip": false,
|
| 858 |
"rstrip": false,
|
| 859 |
+
"normalized": false
|
|
|
|
| 860 |
},
|
| 861 |
{
|
| 862 |
"id": 50352,
|
| 863 |
+
"special": true,
|
| 864 |
"content": "<|haw|>",
|
| 865 |
"single_word": false,
|
| 866 |
"lstrip": false,
|
| 867 |
"rstrip": false,
|
| 868 |
+
"normalized": false
|
|
|
|
| 869 |
},
|
| 870 |
{
|
| 871 |
"id": 50353,
|
| 872 |
+
"special": true,
|
| 873 |
"content": "<|ln|>",
|
| 874 |
"single_word": false,
|
| 875 |
"lstrip": false,
|
| 876 |
"rstrip": false,
|
| 877 |
+
"normalized": false
|
|
|
|
| 878 |
},
|
| 879 |
{
|
| 880 |
"id": 50354,
|
| 881 |
+
"special": true,
|
| 882 |
"content": "<|ha|>",
|
| 883 |
"single_word": false,
|
| 884 |
"lstrip": false,
|
| 885 |
"rstrip": false,
|
| 886 |
+
"normalized": false
|
|
|
|
| 887 |
},
|
| 888 |
{
|
| 889 |
"id": 50355,
|
| 890 |
+
"special": true,
|
| 891 |
"content": "<|ba|>",
|
| 892 |
"single_word": false,
|
| 893 |
"lstrip": false,
|
| 894 |
"rstrip": false,
|
| 895 |
+
"normalized": false
|
|
|
|
| 896 |
},
|
| 897 |
{
|
| 898 |
"id": 50356,
|
| 899 |
+
"special": true,
|
| 900 |
"content": "<|jw|>",
|
| 901 |
"single_word": false,
|
| 902 |
"lstrip": false,
|
| 903 |
"rstrip": false,
|
| 904 |
+
"normalized": false
|
|
|
|
| 905 |
},
|
| 906 |
{
|
| 907 |
"id": 50357,
|
| 908 |
+
"special": true,
|
| 909 |
"content": "<|su|>",
|
| 910 |
"single_word": false,
|
| 911 |
"lstrip": false,
|
| 912 |
"rstrip": false,
|
| 913 |
+
"normalized": false
|
|
|
|
| 914 |
},
|
| 915 |
{
|
| 916 |
"id": 50358,
|
| 917 |
+
"special": true,
|
| 918 |
"content": "<|translate|>",
|
| 919 |
"single_word": false,
|
| 920 |
"lstrip": false,
|
| 921 |
"rstrip": false,
|
| 922 |
+
"normalized": false
|
|
|
|
| 923 |
},
|
| 924 |
{
|
| 925 |
"id": 50359,
|
| 926 |
+
"special": true,
|
| 927 |
"content": "<|transcribe|>",
|
| 928 |
"single_word": false,
|
| 929 |
"lstrip": false,
|
| 930 |
"rstrip": false,
|
| 931 |
+
"normalized": false
|
|
|
|
| 932 |
},
|
| 933 |
{
|
| 934 |
"id": 50360,
|
| 935 |
+
"special": true,
|
| 936 |
"content": "<|startoflm|>",
|
| 937 |
"single_word": false,
|
| 938 |
"lstrip": false,
|
| 939 |
"rstrip": false,
|
| 940 |
+
"normalized": false
|
|
|
|
| 941 |
},
|
| 942 |
{
|
| 943 |
"id": 50361,
|
| 944 |
+
"special": true,
|
| 945 |
"content": "<|startofprev|>",
|
| 946 |
"single_word": false,
|
| 947 |
"lstrip": false,
|
| 948 |
"rstrip": false,
|
| 949 |
+
"normalized": false
|
|
|
|
| 950 |
},
|
| 951 |
{
|
| 952 |
"id": 50362,
|
| 953 |
+
"special": true,
|
| 954 |
"content": "<|nocaptions|>",
|
| 955 |
"single_word": false,
|
| 956 |
"lstrip": false,
|
| 957 |
"rstrip": false,
|
| 958 |
+
"normalized": false
|
|
|
|
| 959 |
},
|
| 960 |
{
|
| 961 |
"id": 50363,
|
| 962 |
+
"special": true,
|
| 963 |
"content": "<|notimestamps|>",
|
| 964 |
"single_word": false,
|
| 965 |
"lstrip": false,
|
| 966 |
"rstrip": false,
|
| 967 |
+
"normalized": false
|
|
|
|
| 968 |
}
|
| 969 |
],
|
| 970 |
"normalizer": null,
|
| 971 |
"pre_tokenizer": {
|
| 972 |
"type": "ByteLevel",
|
| 973 |
"add_prefix_space": false,
|
| 974 |
+
"trim_offsets": true
|
|
|
|
| 975 |
},
|
| 976 |
"post_processor": {
|
| 977 |
"type": "TemplateProcessing",
|
|
|
|
| 1066 |
"decoder": {
|
| 1067 |
"type": "ByteLevel",
|
| 1068 |
"add_prefix_space": true,
|
| 1069 |
+
"trim_offsets": true
|
|
|
|
| 1070 |
},
|
| 1071 |
"model": {
|
| 1072 |
"type": "BPE",
|
quantized/openai/whisper-base/speech2seq-lm-with-past/tokenizer_config.json
CHANGED
|
@@ -19,7 +19,6 @@
|
|
| 19 |
},
|
| 20 |
"errors": "replace",
|
| 21 |
"model_max_length": 448,
|
| 22 |
-
"name_or_path": "openai/whisper-base",
|
| 23 |
"pad_token": null,
|
| 24 |
"processor_class": "WhisperProcessor",
|
| 25 |
"return_attention_mask": false,
|
|
|
|
| 19 |
},
|
| 20 |
"errors": "replace",
|
| 21 |
"model_max_length": 448,
|
|
|
|
| 22 |
"pad_token": null,
|
| 23 |
"processor_class": "WhisperProcessor",
|
| 24 |
"return_attention_mask": false,
|
quantized/openai/whisper-base/speech2seq-lm-with-past/vocab.json
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
quantized/openai/whisper-small.en/default/config.json
CHANGED
|
@@ -2,6 +2,7 @@
|
|
| 2 |
"_name_or_path": "openai/whisper-small.en",
|
| 3 |
"activation_dropout": 0.0,
|
| 4 |
"activation_function": "gelu",
|
|
|
|
| 5 |
"architectures": [
|
| 6 |
"WhisperForConditionalGeneration"
|
| 7 |
],
|
|
@@ -11,6 +12,7 @@
|
|
| 11 |
50256
|
| 12 |
],
|
| 13 |
"bos_token_id": 50257,
|
|
|
|
| 14 |
"d_model": 768,
|
| 15 |
"decoder_attention_heads": 12,
|
| 16 |
"decoder_ffn_dim": 3072,
|
|
@@ -31,6 +33,12 @@
|
|
| 31 |
],
|
| 32 |
"init_std": 0.02,
|
| 33 |
"is_encoder_decoder": true,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 34 |
"max_length": 448,
|
| 35 |
"max_source_positions": 1500,
|
| 36 |
"max_target_positions": 448,
|
|
@@ -129,7 +137,8 @@
|
|
| 129 |
50360,
|
| 130 |
50361
|
| 131 |
],
|
| 132 |
-
"transformers_version": "4.
|
| 133 |
"use_cache": true,
|
|
|
|
| 134 |
"vocab_size": 51864
|
| 135 |
}
|
|
|
|
| 2 |
"_name_or_path": "openai/whisper-small.en",
|
| 3 |
"activation_dropout": 0.0,
|
| 4 |
"activation_function": "gelu",
|
| 5 |
+
"apply_spec_augment": false,
|
| 6 |
"architectures": [
|
| 7 |
"WhisperForConditionalGeneration"
|
| 8 |
],
|
|
|
|
| 12 |
50256
|
| 13 |
],
|
| 14 |
"bos_token_id": 50257,
|
| 15 |
+
"classifier_proj_size": 256,
|
| 16 |
"d_model": 768,
|
| 17 |
"decoder_attention_heads": 12,
|
| 18 |
"decoder_ffn_dim": 3072,
|
|
|
|
| 33 |
],
|
| 34 |
"init_std": 0.02,
|
| 35 |
"is_encoder_decoder": true,
|
| 36 |
+
"mask_feature_length": 10,
|
| 37 |
+
"mask_feature_min_masks": 0,
|
| 38 |
+
"mask_feature_prob": 0.0,
|
| 39 |
+
"mask_time_length": 10,
|
| 40 |
+
"mask_time_min_masks": 2,
|
| 41 |
+
"mask_time_prob": 0.05,
|
| 42 |
"max_length": 448,
|
| 43 |
"max_source_positions": 1500,
|
| 44 |
"max_target_positions": 448,
|
|
|
|
| 137 |
50360,
|
| 138 |
50361
|
| 139 |
],
|
| 140 |
+
"transformers_version": "4.27.2",
|
| 141 |
"use_cache": true,
|
| 142 |
+
"use_weighted_layer_sum": false,
|
| 143 |
"vocab_size": 51864
|
| 144 |
}
|
quantized/openai/whisper-small.en/default/decoder_model.onnx
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:8af023c75b14ede43fa2904e5d702d1ea36673709cb6a0f849d2fb7c498f67f7
|
| 3 |
-
size 156503755
|
|
|
|
|
|
|
|
|
|
|
|
quantized/openai/whisper-small.en/default/encoder_model.onnx
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:6792ba696e505bd3527efa62327024bc04db8bf9558d47e16a2fff7e3810440f
|
| 3 |
-
size 92735928
|
|
|
|
|
|
|
|
|
|
|
|
quantized/openai/whisper-small.en/default/generation_config.json
DELETED
|
@@ -1,111 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"begin_suppress_tokens": [
|
| 3 |
-
220,
|
| 4 |
-
50256
|
| 5 |
-
],
|
| 6 |
-
"bos_token_id": 50257,
|
| 7 |
-
"decoder_start_token_id": 50257,
|
| 8 |
-
"eos_token_id": 50256,
|
| 9 |
-
"forced_decoder_ids": [
|
| 10 |
-
[
|
| 11 |
-
1,
|
| 12 |
-
50362
|
| 13 |
-
]
|
| 14 |
-
],
|
| 15 |
-
"is_multilingual": false,
|
| 16 |
-
"max_initial_timestamp_index": 1,
|
| 17 |
-
"max_length": 448,
|
| 18 |
-
"no_timestamps_token_id": 50362,
|
| 19 |
-
"pad_token_id": 50256,
|
| 20 |
-
"suppress_tokens": [
|
| 21 |
-
1,
|
| 22 |
-
2,
|
| 23 |
-
7,
|
| 24 |
-
8,
|
| 25 |
-
9,
|
| 26 |
-
10,
|
| 27 |
-
14,
|
| 28 |
-
25,
|
| 29 |
-
26,
|
| 30 |
-
27,
|
| 31 |
-
28,
|
| 32 |
-
29,
|
| 33 |
-
31,
|
| 34 |
-
58,
|
| 35 |
-
59,
|
| 36 |
-
60,
|
| 37 |
-
61,
|
| 38 |
-
62,
|
| 39 |
-
63,
|
| 40 |
-
90,
|
| 41 |
-
91,
|
| 42 |
-
92,
|
| 43 |
-
93,
|
| 44 |
-
357,
|
| 45 |
-
366,
|
| 46 |
-
438,
|
| 47 |
-
532,
|
| 48 |
-
685,
|
| 49 |
-
705,
|
| 50 |
-
796,
|
| 51 |
-
930,
|
| 52 |
-
1058,
|
| 53 |
-
1220,
|
| 54 |
-
1267,
|
| 55 |
-
1279,
|
| 56 |
-
1303,
|
| 57 |
-
1343,
|
| 58 |
-
1377,
|
| 59 |
-
1391,
|
| 60 |
-
1635,
|
| 61 |
-
1782,
|
| 62 |
-
1875,
|
| 63 |
-
2162,
|
| 64 |
-
2361,
|
| 65 |
-
2488,
|
| 66 |
-
3467,
|
| 67 |
-
4008,
|
| 68 |
-
4211,
|
| 69 |
-
4600,
|
| 70 |
-
4808,
|
| 71 |
-
5299,
|
| 72 |
-
5855,
|
| 73 |
-
6329,
|
| 74 |
-
7203,
|
| 75 |
-
9609,
|
| 76 |
-
9959,
|
| 77 |
-
10563,
|
| 78 |
-
10786,
|
| 79 |
-
11420,
|
| 80 |
-
11709,
|
| 81 |
-
11907,
|
| 82 |
-
13163,
|
| 83 |
-
13697,
|
| 84 |
-
13700,
|
| 85 |
-
14808,
|
| 86 |
-
15306,
|
| 87 |
-
16410,
|
| 88 |
-
16791,
|
| 89 |
-
17992,
|
| 90 |
-
19203,
|
| 91 |
-
19510,
|
| 92 |
-
20724,
|
| 93 |
-
22305,
|
| 94 |
-
22935,
|
| 95 |
-
27007,
|
| 96 |
-
30109,
|
| 97 |
-
30420,
|
| 98 |
-
33409,
|
| 99 |
-
34949,
|
| 100 |
-
40283,
|
| 101 |
-
40493,
|
| 102 |
-
40549,
|
| 103 |
-
47282,
|
| 104 |
-
49146,
|
| 105 |
-
50257,
|
| 106 |
-
50359,
|
| 107 |
-
50360,
|
| 108 |
-
50361
|
| 109 |
-
],
|
| 110 |
-
"transformers_version": "4.27.0.dev0"
|
| 111 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
quantized/openai/whisper-small.en/default/merges.txt
CHANGED
|
@@ -1,4 +1,4 @@
|
|
| 1 |
-
#version: 0.2
|
| 2 |
Ġ t
|
| 3 |
Ġ a
|
| 4 |
h e
|
|
|
|
| 1 |
+
#version: 0.2 - Trained by `huggingface/tokenizers`
|
| 2 |
Ġ t
|
| 3 |
Ġ a
|
| 4 |
h e
|
quantized/openai/whisper-small.en/default/model.onnx
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c95ab3abd5aec74aefe228e1523cd05f5f28bc6c6f8db7d9a5f8d5c37b14aae6
|
| 3 |
+
size 249190690
|
quantized/openai/whisper-small.en/default/tokenizer.json
CHANGED
|
@@ -5,974 +5,973 @@
|
|
| 5 |
"added_tokens": [
|
| 6 |
{
|
| 7 |
"id": 50256,
|
|
|
|
| 8 |
"content": "<|endoftext|>",
|
| 9 |
"single_word": false,
|
| 10 |
"lstrip": false,
|
| 11 |
"rstrip": false,
|
| 12 |
-
"normalized": false
|
| 13 |
-
"special": true
|
| 14 |
},
|
| 15 |
{
|
| 16 |
"id": 50257,
|
|
|
|
| 17 |
"content": "<|startoftranscript|>",
|
| 18 |
"single_word": false,
|
| 19 |
"lstrip": false,
|
| 20 |
"rstrip": false,
|
| 21 |
-
"normalized": false
|
| 22 |
-
"special": true
|
| 23 |
},
|
| 24 |
{
|
| 25 |
"id": 50258,
|
|
|
|
| 26 |
"content": "<|en|>",
|
| 27 |
"single_word": false,
|
| 28 |
"lstrip": false,
|
| 29 |
"rstrip": false,
|
| 30 |
-
"normalized": false
|
| 31 |
-
"special": true
|
| 32 |
},
|
| 33 |
{
|
| 34 |
"id": 50259,
|
|
|
|
| 35 |
"content": "<|zh|>",
|
| 36 |
"single_word": false,
|
| 37 |
"lstrip": false,
|
| 38 |
"rstrip": false,
|
| 39 |
-
"normalized": false
|
| 40 |
-
"special": true
|
| 41 |
},
|
| 42 |
{
|
| 43 |
"id": 50260,
|
|
|
|
| 44 |
"content": "<|de|>",
|
| 45 |
"single_word": false,
|
| 46 |
"lstrip": false,
|
| 47 |
"rstrip": false,
|
| 48 |
-
"normalized": false
|
| 49 |
-
"special": true
|
| 50 |
},
|
| 51 |
{
|
| 52 |
"id": 50261,
|
|
|
|
| 53 |
"content": "<|es|>",
|
| 54 |
"single_word": false,
|
| 55 |
"lstrip": false,
|
| 56 |
"rstrip": false,
|
| 57 |
-
"normalized": false
|
| 58 |
-
"special": true
|
| 59 |
},
|
| 60 |
{
|
| 61 |
"id": 50262,
|
|
|
|
| 62 |
"content": "<|ru|>",
|
| 63 |
"single_word": false,
|
| 64 |
"lstrip": false,
|
| 65 |
"rstrip": false,
|
| 66 |
-
"normalized": false
|
| 67 |
-
"special": true
|
| 68 |
},
|
| 69 |
{
|
| 70 |
"id": 50263,
|
|
|
|
| 71 |
"content": "<|ko|>",
|
| 72 |
"single_word": false,
|
| 73 |
"lstrip": false,
|
| 74 |
"rstrip": false,
|
| 75 |
-
"normalized": false
|
| 76 |
-
"special": true
|
| 77 |
},
|
| 78 |
{
|
| 79 |
"id": 50264,
|
|
|
|
| 80 |
"content": "<|fr|>",
|
| 81 |
"single_word": false,
|
| 82 |
"lstrip": false,
|
| 83 |
"rstrip": false,
|
| 84 |
-
"normalized": false
|
| 85 |
-
"special": true
|
| 86 |
},
|
| 87 |
{
|
| 88 |
"id": 50265,
|
|
|
|
| 89 |
"content": "<|ja|>",
|
| 90 |
"single_word": false,
|
| 91 |
"lstrip": false,
|
| 92 |
"rstrip": false,
|
| 93 |
-
"normalized": false
|
| 94 |
-
"special": true
|
| 95 |
},
|
| 96 |
{
|
| 97 |
"id": 50266,
|
|
|
|
| 98 |
"content": "<|pt|>",
|
| 99 |
"single_word": false,
|
| 100 |
"lstrip": false,
|
| 101 |
"rstrip": false,
|
| 102 |
-
"normalized": false
|
| 103 |
-
"special": true
|
| 104 |
},
|
| 105 |
{
|
| 106 |
"id": 50267,
|
|
|
|
| 107 |
"content": "<|tr|>",
|
| 108 |
"single_word": false,
|
| 109 |
"lstrip": false,
|
| 110 |
"rstrip": false,
|
| 111 |
-
"normalized": false
|
| 112 |
-
"special": true
|
| 113 |
},
|
| 114 |
{
|
| 115 |
"id": 50268,
|
|
|
|
| 116 |
"content": "<|pl|>",
|
| 117 |
"single_word": false,
|
| 118 |
"lstrip": false,
|
| 119 |
"rstrip": false,
|
| 120 |
-
"normalized": false
|
| 121 |
-
"special": true
|
| 122 |
},
|
| 123 |
{
|
| 124 |
"id": 50269,
|
|
|
|
| 125 |
"content": "<|ca|>",
|
| 126 |
"single_word": false,
|
| 127 |
"lstrip": false,
|
| 128 |
"rstrip": false,
|
| 129 |
-
"normalized": false
|
| 130 |
-
"special": true
|
| 131 |
},
|
| 132 |
{
|
| 133 |
"id": 50270,
|
|
|
|
| 134 |
"content": "<|nl|>",
|
| 135 |
"single_word": false,
|
| 136 |
"lstrip": false,
|
| 137 |
"rstrip": false,
|
| 138 |
-
"normalized": false
|
| 139 |
-
"special": true
|
| 140 |
},
|
| 141 |
{
|
| 142 |
"id": 50271,
|
|
|
|
| 143 |
"content": "<|ar|>",
|
| 144 |
"single_word": false,
|
| 145 |
"lstrip": false,
|
| 146 |
"rstrip": false,
|
| 147 |
-
"normalized": false
|
| 148 |
-
"special": true
|
| 149 |
},
|
| 150 |
{
|
| 151 |
"id": 50272,
|
|
|
|
| 152 |
"content": "<|sv|>",
|
| 153 |
"single_word": false,
|
| 154 |
"lstrip": false,
|
| 155 |
"rstrip": false,
|
| 156 |
-
"normalized": false
|
| 157 |
-
"special": true
|
| 158 |
},
|
| 159 |
{
|
| 160 |
"id": 50273,
|
|
|
|
| 161 |
"content": "<|it|>",
|
| 162 |
"single_word": false,
|
| 163 |
"lstrip": false,
|
| 164 |
"rstrip": false,
|
| 165 |
-
"normalized": false
|
| 166 |
-
"special": true
|
| 167 |
},
|
| 168 |
{
|
| 169 |
"id": 50274,
|
|
|
|
| 170 |
"content": "<|id|>",
|
| 171 |
"single_word": false,
|
| 172 |
"lstrip": false,
|
| 173 |
"rstrip": false,
|
| 174 |
-
"normalized": false
|
| 175 |
-
"special": true
|
| 176 |
},
|
| 177 |
{
|
| 178 |
"id": 50275,
|
|
|
|
| 179 |
"content": "<|hi|>",
|
| 180 |
"single_word": false,
|
| 181 |
"lstrip": false,
|
| 182 |
"rstrip": false,
|
| 183 |
-
"normalized": false
|
| 184 |
-
"special": true
|
| 185 |
},
|
| 186 |
{
|
| 187 |
"id": 50276,
|
|
|
|
| 188 |
"content": "<|fi|>",
|
| 189 |
"single_word": false,
|
| 190 |
"lstrip": false,
|
| 191 |
"rstrip": false,
|
| 192 |
-
"normalized": false
|
| 193 |
-
"special": true
|
| 194 |
},
|
| 195 |
{
|
| 196 |
"id": 50277,
|
|
|
|
| 197 |
"content": "<|vi|>",
|
| 198 |
"single_word": false,
|
| 199 |
"lstrip": false,
|
| 200 |
"rstrip": false,
|
| 201 |
-
"normalized": false
|
| 202 |
-
"special": true
|
| 203 |
},
|
| 204 |
{
|
| 205 |
"id": 50278,
|
|
|
|
| 206 |
"content": "<|iw|>",
|
| 207 |
"single_word": false,
|
| 208 |
"lstrip": false,
|
| 209 |
"rstrip": false,
|
| 210 |
-
"normalized": false
|
| 211 |
-
"special": true
|
| 212 |
},
|
| 213 |
{
|
| 214 |
"id": 50279,
|
|
|
|
| 215 |
"content": "<|uk|>",
|
| 216 |
"single_word": false,
|
| 217 |
"lstrip": false,
|
| 218 |
"rstrip": false,
|
| 219 |
-
"normalized": false
|
| 220 |
-
"special": true
|
| 221 |
},
|
| 222 |
{
|
| 223 |
"id": 50280,
|
|
|
|
| 224 |
"content": "<|el|>",
|
| 225 |
"single_word": false,
|
| 226 |
"lstrip": false,
|
| 227 |
"rstrip": false,
|
| 228 |
-
"normalized": false
|
| 229 |
-
"special": true
|
| 230 |
},
|
| 231 |
{
|
| 232 |
"id": 50281,
|
|
|
|
| 233 |
"content": "<|ms|>",
|
| 234 |
"single_word": false,
|
| 235 |
"lstrip": false,
|
| 236 |
"rstrip": false,
|
| 237 |
-
"normalized": false
|
| 238 |
-
"special": true
|
| 239 |
},
|
| 240 |
{
|
| 241 |
"id": 50282,
|
|
|
|
| 242 |
"content": "<|cs|>",
|
| 243 |
"single_word": false,
|
| 244 |
"lstrip": false,
|
| 245 |
"rstrip": false,
|
| 246 |
-
"normalized": false
|
| 247 |
-
"special": true
|
| 248 |
},
|
| 249 |
{
|
| 250 |
"id": 50283,
|
|
|
|
| 251 |
"content": "<|ro|>",
|
| 252 |
"single_word": false,
|
| 253 |
"lstrip": false,
|
| 254 |
"rstrip": false,
|
| 255 |
-
"normalized": false
|
| 256 |
-
"special": true
|
| 257 |
},
|
| 258 |
{
|
| 259 |
"id": 50284,
|
|
|
|
| 260 |
"content": "<|da|>",
|
| 261 |
"single_word": false,
|
| 262 |
"lstrip": false,
|
| 263 |
"rstrip": false,
|
| 264 |
-
"normalized": false
|
| 265 |
-
"special": true
|
| 266 |
},
|
| 267 |
{
|
| 268 |
"id": 50285,
|
|
|
|
| 269 |
"content": "<|hu|>",
|
| 270 |
"single_word": false,
|
| 271 |
"lstrip": false,
|
| 272 |
"rstrip": false,
|
| 273 |
-
"normalized": false
|
| 274 |
-
"special": true
|
| 275 |
},
|
| 276 |
{
|
| 277 |
"id": 50286,
|
|
|
|
| 278 |
"content": "<|ta|>",
|
| 279 |
"single_word": false,
|
| 280 |
"lstrip": false,
|
| 281 |
"rstrip": false,
|
| 282 |
-
"normalized": false
|
| 283 |
-
"special": true
|
| 284 |
},
|
| 285 |
{
|
| 286 |
"id": 50287,
|
|
|
|
| 287 |
"content": "<|no|>",
|
| 288 |
"single_word": false,
|
| 289 |
"lstrip": false,
|
| 290 |
"rstrip": false,
|
| 291 |
-
"normalized": false
|
| 292 |
-
"special": true
|
| 293 |
},
|
| 294 |
{
|
| 295 |
"id": 50288,
|
|
|
|
| 296 |
"content": "<|th|>",
|
| 297 |
"single_word": false,
|
| 298 |
"lstrip": false,
|
| 299 |
"rstrip": false,
|
| 300 |
-
"normalized": false
|
| 301 |
-
"special": true
|
| 302 |
},
|
| 303 |
{
|
| 304 |
"id": 50289,
|
|
|
|
| 305 |
"content": "<|ur|>",
|
| 306 |
"single_word": false,
|
| 307 |
"lstrip": false,
|
| 308 |
"rstrip": false,
|
| 309 |
-
"normalized": false
|
| 310 |
-
"special": true
|
| 311 |
},
|
| 312 |
{
|
| 313 |
"id": 50290,
|
|
|
|
| 314 |
"content": "<|hr|>",
|
| 315 |
"single_word": false,
|
| 316 |
"lstrip": false,
|
| 317 |
"rstrip": false,
|
| 318 |
-
"normalized": false
|
| 319 |
-
"special": true
|
| 320 |
},
|
| 321 |
{
|
| 322 |
"id": 50291,
|
|
|
|
| 323 |
"content": "<|bg|>",
|
| 324 |
"single_word": false,
|
| 325 |
"lstrip": false,
|
| 326 |
"rstrip": false,
|
| 327 |
-
"normalized": false
|
| 328 |
-
"special": true
|
| 329 |
},
|
| 330 |
{
|
| 331 |
"id": 50292,
|
|
|
|
| 332 |
"content": "<|lt|>",
|
| 333 |
"single_word": false,
|
| 334 |
"lstrip": false,
|
| 335 |
"rstrip": false,
|
| 336 |
-
"normalized": false
|
| 337 |
-
"special": true
|
| 338 |
},
|
| 339 |
{
|
| 340 |
"id": 50293,
|
|
|
|
| 341 |
"content": "<|la|>",
|
| 342 |
"single_word": false,
|
| 343 |
"lstrip": false,
|
| 344 |
"rstrip": false,
|
| 345 |
-
"normalized": false
|
| 346 |
-
"special": true
|
| 347 |
},
|
| 348 |
{
|
| 349 |
"id": 50294,
|
|
|
|
| 350 |
"content": "<|mi|>",
|
| 351 |
"single_word": false,
|
| 352 |
"lstrip": false,
|
| 353 |
"rstrip": false,
|
| 354 |
-
"normalized": false
|
| 355 |
-
"special": true
|
| 356 |
},
|
| 357 |
{
|
| 358 |
"id": 50295,
|
|
|
|
| 359 |
"content": "<|ml|>",
|
| 360 |
"single_word": false,
|
| 361 |
"lstrip": false,
|
| 362 |
"rstrip": false,
|
| 363 |
-
"normalized": false
|
| 364 |
-
"special": true
|
| 365 |
},
|
| 366 |
{
|
| 367 |
"id": 50296,
|
|
|
|
| 368 |
"content": "<|cy|>",
|
| 369 |
"single_word": false,
|
| 370 |
"lstrip": false,
|
| 371 |
"rstrip": false,
|
| 372 |
-
"normalized": false
|
| 373 |
-
"special": true
|
| 374 |
},
|
| 375 |
{
|
| 376 |
"id": 50297,
|
|
|
|
| 377 |
"content": "<|sk|>",
|
| 378 |
"single_word": false,
|
| 379 |
"lstrip": false,
|
| 380 |
"rstrip": false,
|
| 381 |
-
"normalized": false
|
| 382 |
-
"special": true
|
| 383 |
},
|
| 384 |
{
|
| 385 |
"id": 50298,
|
|
|
|
| 386 |
"content": "<|te|>",
|
| 387 |
"single_word": false,
|
| 388 |
"lstrip": false,
|
| 389 |
"rstrip": false,
|
| 390 |
-
"normalized": false
|
| 391 |
-
"special": true
|
| 392 |
},
|
| 393 |
{
|
| 394 |
"id": 50299,
|
|
|
|
| 395 |
"content": "<|fa|>",
|
| 396 |
"single_word": false,
|
| 397 |
"lstrip": false,
|
| 398 |
"rstrip": false,
|
| 399 |
-
"normalized": false
|
| 400 |
-
"special": true
|
| 401 |
},
|
| 402 |
{
|
| 403 |
"id": 50300,
|
|
|
|
| 404 |
"content": "<|lv|>",
|
| 405 |
"single_word": false,
|
| 406 |
"lstrip": false,
|
| 407 |
"rstrip": false,
|
| 408 |
-
"normalized": false
|
| 409 |
-
"special": true
|
| 410 |
},
|
| 411 |
{
|
| 412 |
"id": 50301,
|
|
|
|
| 413 |
"content": "<|bn|>",
|
| 414 |
"single_word": false,
|
| 415 |
"lstrip": false,
|
| 416 |
"rstrip": false,
|
| 417 |
-
"normalized": false
|
| 418 |
-
"special": true
|
| 419 |
},
|
| 420 |
{
|
| 421 |
"id": 50302,
|
|
|
|
| 422 |
"content": "<|sr|>",
|
| 423 |
"single_word": false,
|
| 424 |
"lstrip": false,
|
| 425 |
"rstrip": false,
|
| 426 |
-
"normalized": false
|
| 427 |
-
"special": true
|
| 428 |
},
|
| 429 |
{
|
| 430 |
"id": 50303,
|
|
|
|
| 431 |
"content": "<|az|>",
|
| 432 |
"single_word": false,
|
| 433 |
"lstrip": false,
|
| 434 |
"rstrip": false,
|
| 435 |
-
"normalized": false
|
| 436 |
-
"special": true
|
| 437 |
},
|
| 438 |
{
|
| 439 |
"id": 50304,
|
|
|
|
| 440 |
"content": "<|sl|>",
|
| 441 |
"single_word": false,
|
| 442 |
"lstrip": false,
|
| 443 |
"rstrip": false,
|
| 444 |
-
"normalized": false
|
| 445 |
-
"special": true
|
| 446 |
},
|
| 447 |
{
|
| 448 |
"id": 50305,
|
|
|
|
| 449 |
"content": "<|kn|>",
|
| 450 |
"single_word": false,
|
| 451 |
"lstrip": false,
|
| 452 |
"rstrip": false,
|
| 453 |
-
"normalized": false
|
| 454 |
-
"special": true
|
| 455 |
},
|
| 456 |
{
|
| 457 |
"id": 50306,
|
|
|
|
| 458 |
"content": "<|et|>",
|
| 459 |
"single_word": false,
|
| 460 |
"lstrip": false,
|
| 461 |
"rstrip": false,
|
| 462 |
-
"normalized": false
|
| 463 |
-
"special": true
|
| 464 |
},
|
| 465 |
{
|
| 466 |
"id": 50307,
|
|
|
|
| 467 |
"content": "<|mk|>",
|
| 468 |
"single_word": false,
|
| 469 |
"lstrip": false,
|
| 470 |
"rstrip": false,
|
| 471 |
-
"normalized": false
|
| 472 |
-
"special": true
|
| 473 |
},
|
| 474 |
{
|
| 475 |
"id": 50308,
|
|
|
|
| 476 |
"content": "<|br|>",
|
| 477 |
"single_word": false,
|
| 478 |
"lstrip": false,
|
| 479 |
"rstrip": false,
|
| 480 |
-
"normalized": false
|
| 481 |
-
"special": true
|
| 482 |
},
|
| 483 |
{
|
| 484 |
"id": 50309,
|
|
|
|
| 485 |
"content": "<|eu|>",
|
| 486 |
"single_word": false,
|
| 487 |
"lstrip": false,
|
| 488 |
"rstrip": false,
|
| 489 |
-
"normalized": false
|
| 490 |
-
"special": true
|
| 491 |
},
|
| 492 |
{
|
| 493 |
"id": 50310,
|
|
|
|
| 494 |
"content": "<|is|>",
|
| 495 |
"single_word": false,
|
| 496 |
"lstrip": false,
|
| 497 |
"rstrip": false,
|
| 498 |
-
"normalized": false
|
| 499 |
-
"special": true
|
| 500 |
},
|
| 501 |
{
|
| 502 |
"id": 50311,
|
|
|
|
| 503 |
"content": "<|hy|>",
|
| 504 |
"single_word": false,
|
| 505 |
"lstrip": false,
|
| 506 |
"rstrip": false,
|
| 507 |
-
"normalized": false
|
| 508 |
-
"special": true
|
| 509 |
},
|
| 510 |
{
|
| 511 |
"id": 50312,
|
|
|
|
| 512 |
"content": "<|ne|>",
|
| 513 |
"single_word": false,
|
| 514 |
"lstrip": false,
|
| 515 |
"rstrip": false,
|
| 516 |
-
"normalized": false
|
| 517 |
-
"special": true
|
| 518 |
},
|
| 519 |
{
|
| 520 |
"id": 50313,
|
|
|
|
| 521 |
"content": "<|mn|>",
|
| 522 |
"single_word": false,
|
| 523 |
"lstrip": false,
|
| 524 |
"rstrip": false,
|
| 525 |
-
"normalized": false
|
| 526 |
-
"special": true
|
| 527 |
},
|
| 528 |
{
|
| 529 |
"id": 50314,
|
|
|
|
| 530 |
"content": "<|bs|>",
|
| 531 |
"single_word": false,
|
| 532 |
"lstrip": false,
|
| 533 |
"rstrip": false,
|
| 534 |
-
"normalized": false
|
| 535 |
-
"special": true
|
| 536 |
},
|
| 537 |
{
|
| 538 |
"id": 50315,
|
|
|
|
| 539 |
"content": "<|kk|>",
|
| 540 |
"single_word": false,
|
| 541 |
"lstrip": false,
|
| 542 |
"rstrip": false,
|
| 543 |
-
"normalized": false
|
| 544 |
-
"special": true
|
| 545 |
},
|
| 546 |
{
|
| 547 |
"id": 50316,
|
|
|
|
| 548 |
"content": "<|sq|>",
|
| 549 |
"single_word": false,
|
| 550 |
"lstrip": false,
|
| 551 |
"rstrip": false,
|
| 552 |
-
"normalized": false
|
| 553 |
-
"special": true
|
| 554 |
},
|
| 555 |
{
|
| 556 |
"id": 50317,
|
|
|
|
| 557 |
"content": "<|sw|>",
|
| 558 |
"single_word": false,
|
| 559 |
"lstrip": false,
|
| 560 |
"rstrip": false,
|
| 561 |
-
"normalized": false
|
| 562 |
-
"special": true
|
| 563 |
},
|
| 564 |
{
|
| 565 |
"id": 50318,
|
|
|
|
| 566 |
"content": "<|gl|>",
|
| 567 |
"single_word": false,
|
| 568 |
"lstrip": false,
|
| 569 |
"rstrip": false,
|
| 570 |
-
"normalized": false
|
| 571 |
-
"special": true
|
| 572 |
},
|
| 573 |
{
|
| 574 |
"id": 50319,
|
|
|
|
| 575 |
"content": "<|mr|>",
|
| 576 |
"single_word": false,
|
| 577 |
"lstrip": false,
|
| 578 |
"rstrip": false,
|
| 579 |
-
"normalized": false
|
| 580 |
-
"special": true
|
| 581 |
},
|
| 582 |
{
|
| 583 |
"id": 50320,
|
|
|
|
| 584 |
"content": "<|pa|>",
|
| 585 |
"single_word": false,
|
| 586 |
"lstrip": false,
|
| 587 |
"rstrip": false,
|
| 588 |
-
"normalized": false
|
| 589 |
-
"special": true
|
| 590 |
},
|
| 591 |
{
|
| 592 |
"id": 50321,
|
|
|
|
| 593 |
"content": "<|si|>",
|
| 594 |
"single_word": false,
|
| 595 |
"lstrip": false,
|
| 596 |
"rstrip": false,
|
| 597 |
-
"normalized": false
|
| 598 |
-
"special": true
|
| 599 |
},
|
| 600 |
{
|
| 601 |
"id": 50322,
|
|
|
|
| 602 |
"content": "<|km|>",
|
| 603 |
"single_word": false,
|
| 604 |
"lstrip": false,
|
| 605 |
"rstrip": false,
|
| 606 |
-
"normalized": false
|
| 607 |
-
"special": true
|
| 608 |
},
|
| 609 |
{
|
| 610 |
"id": 50323,
|
|
|
|
| 611 |
"content": "<|sn|>",
|
| 612 |
"single_word": false,
|
| 613 |
"lstrip": false,
|
| 614 |
"rstrip": false,
|
| 615 |
-
"normalized": false
|
| 616 |
-
"special": true
|
| 617 |
},
|
| 618 |
{
|
| 619 |
"id": 50324,
|
|
|
|
| 620 |
"content": "<|yo|>",
|
| 621 |
"single_word": false,
|
| 622 |
"lstrip": false,
|
| 623 |
"rstrip": false,
|
| 624 |
-
"normalized": false
|
| 625 |
-
"special": true
|
| 626 |
},
|
| 627 |
{
|
| 628 |
"id": 50325,
|
|
|
|
| 629 |
"content": "<|so|>",
|
| 630 |
"single_word": false,
|
| 631 |
"lstrip": false,
|
| 632 |
"rstrip": false,
|
| 633 |
-
"normalized": false
|
| 634 |
-
"special": true
|
| 635 |
},
|
| 636 |
{
|
| 637 |
"id": 50326,
|
|
|
|
| 638 |
"content": "<|af|>",
|
| 639 |
"single_word": false,
|
| 640 |
"lstrip": false,
|
| 641 |
"rstrip": false,
|
| 642 |
-
"normalized": false
|
| 643 |
-
"special": true
|
| 644 |
},
|
| 645 |
{
|
| 646 |
"id": 50327,
|
|
|
|
| 647 |
"content": "<|oc|>",
|
| 648 |
"single_word": false,
|
| 649 |
"lstrip": false,
|
| 650 |
"rstrip": false,
|
| 651 |
-
"normalized": false
|
| 652 |
-
"special": true
|
| 653 |
},
|
| 654 |
{
|
| 655 |
"id": 50328,
|
|
|
|
| 656 |
"content": "<|ka|>",
|
| 657 |
"single_word": false,
|
| 658 |
"lstrip": false,
|
| 659 |
"rstrip": false,
|
| 660 |
-
"normalized": false
|
| 661 |
-
"special": true
|
| 662 |
},
|
| 663 |
{
|
| 664 |
"id": 50329,
|
|
|
|
| 665 |
"content": "<|be|>",
|
| 666 |
"single_word": false,
|
| 667 |
"lstrip": false,
|
| 668 |
"rstrip": false,
|
| 669 |
-
"normalized": false
|
| 670 |
-
"special": true
|
| 671 |
},
|
| 672 |
{
|
| 673 |
"id": 50330,
|
|
|
|
| 674 |
"content": "<|tg|>",
|
| 675 |
"single_word": false,
|
| 676 |
"lstrip": false,
|
| 677 |
"rstrip": false,
|
| 678 |
-
"normalized": false
|
| 679 |
-
"special": true
|
| 680 |
},
|
| 681 |
{
|
| 682 |
"id": 50331,
|
|
|
|
| 683 |
"content": "<|sd|>",
|
| 684 |
"single_word": false,
|
| 685 |
"lstrip": false,
|
| 686 |
"rstrip": false,
|
| 687 |
-
"normalized": false
|
| 688 |
-
"special": true
|
| 689 |
},
|
| 690 |
{
|
| 691 |
"id": 50332,
|
|
|
|
| 692 |
"content": "<|gu|>",
|
| 693 |
"single_word": false,
|
| 694 |
"lstrip": false,
|
| 695 |
"rstrip": false,
|
| 696 |
-
"normalized": false
|
| 697 |
-
"special": true
|
| 698 |
},
|
| 699 |
{
|
| 700 |
"id": 50333,
|
|
|
|
| 701 |
"content": "<|am|>",
|
| 702 |
"single_word": false,
|
| 703 |
"lstrip": false,
|
| 704 |
"rstrip": false,
|
| 705 |
-
"normalized": false
|
| 706 |
-
"special": true
|
| 707 |
},
|
| 708 |
{
|
| 709 |
"id": 50334,
|
|
|
|
| 710 |
"content": "<|yi|>",
|
| 711 |
"single_word": false,
|
| 712 |
"lstrip": false,
|
| 713 |
"rstrip": false,
|
| 714 |
-
"normalized": false
|
| 715 |
-
"special": true
|
| 716 |
},
|
| 717 |
{
|
| 718 |
"id": 50335,
|
|
|
|
| 719 |
"content": "<|lo|>",
|
| 720 |
"single_word": false,
|
| 721 |
"lstrip": false,
|
| 722 |
"rstrip": false,
|
| 723 |
-
"normalized": false
|
| 724 |
-
"special": true
|
| 725 |
},
|
| 726 |
{
|
| 727 |
"id": 50336,
|
|
|
|
| 728 |
"content": "<|uz|>",
|
| 729 |
"single_word": false,
|
| 730 |
"lstrip": false,
|
| 731 |
"rstrip": false,
|
| 732 |
-
"normalized": false
|
| 733 |
-
"special": true
|
| 734 |
},
|
| 735 |
{
|
| 736 |
"id": 50337,
|
|
|
|
| 737 |
"content": "<|fo|>",
|
| 738 |
"single_word": false,
|
| 739 |
"lstrip": false,
|
| 740 |
"rstrip": false,
|
| 741 |
-
"normalized": false
|
| 742 |
-
"special": true
|
| 743 |
},
|
| 744 |
{
|
| 745 |
"id": 50338,
|
|
|
|
| 746 |
"content": "<|ht|>",
|
| 747 |
"single_word": false,
|
| 748 |
"lstrip": false,
|
| 749 |
"rstrip": false,
|
| 750 |
-
"normalized": false
|
| 751 |
-
"special": true
|
| 752 |
},
|
| 753 |
{
|
| 754 |
"id": 50339,
|
|
|
|
| 755 |
"content": "<|ps|>",
|
| 756 |
"single_word": false,
|
| 757 |
"lstrip": false,
|
| 758 |
"rstrip": false,
|
| 759 |
-
"normalized": false
|
| 760 |
-
"special": true
|
| 761 |
},
|
| 762 |
{
|
| 763 |
"id": 50340,
|
|
|
|
| 764 |
"content": "<|tk|>",
|
| 765 |
"single_word": false,
|
| 766 |
"lstrip": false,
|
| 767 |
"rstrip": false,
|
| 768 |
-
"normalized": false
|
| 769 |
-
"special": true
|
| 770 |
},
|
| 771 |
{
|
| 772 |
"id": 50341,
|
|
|
|
| 773 |
"content": "<|nn|>",
|
| 774 |
"single_word": false,
|
| 775 |
"lstrip": false,
|
| 776 |
"rstrip": false,
|
| 777 |
-
"normalized": false
|
| 778 |
-
"special": true
|
| 779 |
},
|
| 780 |
{
|
| 781 |
"id": 50342,
|
|
|
|
| 782 |
"content": "<|mt|>",
|
| 783 |
"single_word": false,
|
| 784 |
"lstrip": false,
|
| 785 |
"rstrip": false,
|
| 786 |
-
"normalized": false
|
| 787 |
-
"special": true
|
| 788 |
},
|
| 789 |
{
|
| 790 |
"id": 50343,
|
|
|
|
| 791 |
"content": "<|sa|>",
|
| 792 |
"single_word": false,
|
| 793 |
"lstrip": false,
|
| 794 |
"rstrip": false,
|
| 795 |
-
"normalized": false
|
| 796 |
-
"special": true
|
| 797 |
},
|
| 798 |
{
|
| 799 |
"id": 50344,
|
|
|
|
| 800 |
"content": "<|lb|>",
|
| 801 |
"single_word": false,
|
| 802 |
"lstrip": false,
|
| 803 |
"rstrip": false,
|
| 804 |
-
"normalized": false
|
| 805 |
-
"special": true
|
| 806 |
},
|
| 807 |
{
|
| 808 |
"id": 50345,
|
|
|
|
| 809 |
"content": "<|my|>",
|
| 810 |
"single_word": false,
|
| 811 |
"lstrip": false,
|
| 812 |
"rstrip": false,
|
| 813 |
-
"normalized": false
|
| 814 |
-
"special": true
|
| 815 |
},
|
| 816 |
{
|
| 817 |
"id": 50346,
|
|
|
|
| 818 |
"content": "<|bo|>",
|
| 819 |
"single_word": false,
|
| 820 |
"lstrip": false,
|
| 821 |
"rstrip": false,
|
| 822 |
-
"normalized": false
|
| 823 |
-
"special": true
|
| 824 |
},
|
| 825 |
{
|
| 826 |
"id": 50347,
|
|
|
|
| 827 |
"content": "<|tl|>",
|
| 828 |
"single_word": false,
|
| 829 |
"lstrip": false,
|
| 830 |
"rstrip": false,
|
| 831 |
-
"normalized": false
|
| 832 |
-
"special": true
|
| 833 |
},
|
| 834 |
{
|
| 835 |
"id": 50348,
|
|
|
|
| 836 |
"content": "<|mg|>",
|
| 837 |
"single_word": false,
|
| 838 |
"lstrip": false,
|
| 839 |
"rstrip": false,
|
| 840 |
-
"normalized": false
|
| 841 |
-
"special": true
|
| 842 |
},
|
| 843 |
{
|
| 844 |
"id": 50349,
|
|
|
|
| 845 |
"content": "<|as|>",
|
| 846 |
"single_word": false,
|
| 847 |
"lstrip": false,
|
| 848 |
"rstrip": false,
|
| 849 |
-
"normalized": false
|
| 850 |
-
"special": true
|
| 851 |
},
|
| 852 |
{
|
| 853 |
"id": 50350,
|
|
|
|
| 854 |
"content": "<|tt|>",
|
| 855 |
"single_word": false,
|
| 856 |
"lstrip": false,
|
| 857 |
"rstrip": false,
|
| 858 |
-
"normalized": false
|
| 859 |
-
"special": true
|
| 860 |
},
|
| 861 |
{
|
| 862 |
"id": 50351,
|
|
|
|
| 863 |
"content": "<|haw|>",
|
| 864 |
"single_word": false,
|
| 865 |
"lstrip": false,
|
| 866 |
"rstrip": false,
|
| 867 |
-
"normalized": false
|
| 868 |
-
"special": true
|
| 869 |
},
|
| 870 |
{
|
| 871 |
"id": 50352,
|
|
|
|
| 872 |
"content": "<|ln|>",
|
| 873 |
"single_word": false,
|
| 874 |
"lstrip": false,
|
| 875 |
"rstrip": false,
|
| 876 |
-
"normalized": false
|
| 877 |
-
"special": true
|
| 878 |
},
|
| 879 |
{
|
| 880 |
"id": 50353,
|
|
|
|
| 881 |
"content": "<|ha|>",
|
| 882 |
"single_word": false,
|
| 883 |
"lstrip": false,
|
| 884 |
"rstrip": false,
|
| 885 |
-
"normalized": false
|
| 886 |
-
"special": true
|
| 887 |
},
|
| 888 |
{
|
| 889 |
"id": 50354,
|
|
|
|
| 890 |
"content": "<|ba|>",
|
| 891 |
"single_word": false,
|
| 892 |
"lstrip": false,
|
| 893 |
"rstrip": false,
|
| 894 |
-
"normalized": false
|
| 895 |
-
"special": true
|
| 896 |
},
|
| 897 |
{
|
| 898 |
"id": 50355,
|
|
|
|
| 899 |
"content": "<|jw|>",
|
| 900 |
"single_word": false,
|
| 901 |
"lstrip": false,
|
| 902 |
"rstrip": false,
|
| 903 |
-
"normalized": false
|
| 904 |
-
"special": true
|
| 905 |
},
|
| 906 |
{
|
| 907 |
"id": 50356,
|
|
|
|
| 908 |
"content": "<|su|>",
|
| 909 |
"single_word": false,
|
| 910 |
"lstrip": false,
|
| 911 |
"rstrip": false,
|
| 912 |
-
"normalized": false
|
| 913 |
-
"special": true
|
| 914 |
},
|
| 915 |
{
|
| 916 |
"id": 50357,
|
|
|
|
| 917 |
"content": "<|translate|>",
|
| 918 |
"single_word": false,
|
| 919 |
"lstrip": false,
|
| 920 |
"rstrip": false,
|
| 921 |
-
"normalized": false
|
| 922 |
-
"special": true
|
| 923 |
},
|
| 924 |
{
|
| 925 |
"id": 50358,
|
|
|
|
| 926 |
"content": "<|transcribe|>",
|
| 927 |
"single_word": false,
|
| 928 |
"lstrip": false,
|
| 929 |
"rstrip": false,
|
| 930 |
-
"normalized": false
|
| 931 |
-
"special": true
|
| 932 |
},
|
| 933 |
{
|
| 934 |
"id": 50359,
|
|
|
|
| 935 |
"content": "<|startoflm|>",
|
| 936 |
"single_word": false,
|
| 937 |
"lstrip": false,
|
| 938 |
"rstrip": false,
|
| 939 |
-
"normalized": false
|
| 940 |
-
"special": true
|
| 941 |
},
|
| 942 |
{
|
| 943 |
"id": 50360,
|
|
|
|
| 944 |
"content": "<|startofprev|>",
|
| 945 |
"single_word": false,
|
| 946 |
"lstrip": false,
|
| 947 |
"rstrip": false,
|
| 948 |
-
"normalized": false
|
| 949 |
-
"special": true
|
| 950 |
},
|
| 951 |
{
|
| 952 |
"id": 50361,
|
|
|
|
| 953 |
"content": "<|nocaptions|>",
|
| 954 |
"single_word": false,
|
| 955 |
"lstrip": false,
|
| 956 |
"rstrip": false,
|
| 957 |
-
"normalized": false
|
| 958 |
-
"special": true
|
| 959 |
},
|
| 960 |
{
|
| 961 |
"id": 50362,
|
|
|
|
| 962 |
"content": "<|notimestamps|>",
|
| 963 |
"single_word": false,
|
| 964 |
"lstrip": false,
|
| 965 |
"rstrip": false,
|
| 966 |
-
"normalized": false
|
| 967 |
-
"special": true
|
| 968 |
}
|
| 969 |
],
|
| 970 |
"normalizer": null,
|
| 971 |
"pre_tokenizer": {
|
| 972 |
"type": "ByteLevel",
|
| 973 |
"add_prefix_space": false,
|
| 974 |
-
"trim_offsets": true
|
| 975 |
-
"use_regex": true
|
| 976 |
},
|
| 977 |
"post_processor": {
|
| 978 |
"type": "TemplateProcessing",
|
|
@@ -1067,8 +1066,7 @@
|
|
| 1067 |
"decoder": {
|
| 1068 |
"type": "ByteLevel",
|
| 1069 |
"add_prefix_space": true,
|
| 1070 |
-
"trim_offsets": true
|
| 1071 |
-
"use_regex": true
|
| 1072 |
},
|
| 1073 |
"model": {
|
| 1074 |
"type": "BPE",
|
|
|
|
| 5 |
"added_tokens": [
|
| 6 |
{
|
| 7 |
"id": 50256,
|
| 8 |
+
"special": true,
|
| 9 |
"content": "<|endoftext|>",
|
| 10 |
"single_word": false,
|
| 11 |
"lstrip": false,
|
| 12 |
"rstrip": false,
|
| 13 |
+
"normalized": false
|
|
|
|
| 14 |
},
|
| 15 |
{
|
| 16 |
"id": 50257,
|
| 17 |
+
"special": true,
|
| 18 |
"content": "<|startoftranscript|>",
|
| 19 |
"single_word": false,
|
| 20 |
"lstrip": false,
|
| 21 |
"rstrip": false,
|
| 22 |
+
"normalized": false
|
|
|
|
| 23 |
},
|
| 24 |
{
|
| 25 |
"id": 50258,
|
| 26 |
+
"special": true,
|
| 27 |
"content": "<|en|>",
|
| 28 |
"single_word": false,
|
| 29 |
"lstrip": false,
|
| 30 |
"rstrip": false,
|
| 31 |
+
"normalized": false
|
|
|
|
| 32 |
},
|
| 33 |
{
|
| 34 |
"id": 50259,
|
| 35 |
+
"special": true,
|
| 36 |
"content": "<|zh|>",
|
| 37 |
"single_word": false,
|
| 38 |
"lstrip": false,
|
| 39 |
"rstrip": false,
|
| 40 |
+
"normalized": false
|
|
|
|
| 41 |
},
|
| 42 |
{
|
| 43 |
"id": 50260,
|
| 44 |
+
"special": true,
|
| 45 |
"content": "<|de|>",
|
| 46 |
"single_word": false,
|
| 47 |
"lstrip": false,
|
| 48 |
"rstrip": false,
|
| 49 |
+
"normalized": false
|
|
|
|
| 50 |
},
|
| 51 |
{
|
| 52 |
"id": 50261,
|
| 53 |
+
"special": true,
|
| 54 |
"content": "<|es|>",
|
| 55 |
"single_word": false,
|
| 56 |
"lstrip": false,
|
| 57 |
"rstrip": false,
|
| 58 |
+
"normalized": false
|
|
|
|
| 59 |
},
|
| 60 |
{
|
| 61 |
"id": 50262,
|
| 62 |
+
"special": true,
|
| 63 |
"content": "<|ru|>",
|
| 64 |
"single_word": false,
|
| 65 |
"lstrip": false,
|
| 66 |
"rstrip": false,
|
| 67 |
+
"normalized": false
|
|
|
|
| 68 |
},
|
| 69 |
{
|
| 70 |
"id": 50263,
|
| 71 |
+
"special": true,
|
| 72 |
"content": "<|ko|>",
|
| 73 |
"single_word": false,
|
| 74 |
"lstrip": false,
|
| 75 |
"rstrip": false,
|
| 76 |
+
"normalized": false
|
|
|
|
| 77 |
},
|
| 78 |
{
|
| 79 |
"id": 50264,
|
| 80 |
+
"special": true,
|
| 81 |
"content": "<|fr|>",
|
| 82 |
"single_word": false,
|
| 83 |
"lstrip": false,
|
| 84 |
"rstrip": false,
|
| 85 |
+
"normalized": false
|
|
|
|
| 86 |
},
|
| 87 |
{
|
| 88 |
"id": 50265,
|
| 89 |
+
"special": true,
|
| 90 |
"content": "<|ja|>",
|
| 91 |
"single_word": false,
|
| 92 |
"lstrip": false,
|
| 93 |
"rstrip": false,
|
| 94 |
+
"normalized": false
|
|
|
|
| 95 |
},
|
| 96 |
{
|
| 97 |
"id": 50266,
|
| 98 |
+
"special": true,
|
| 99 |
"content": "<|pt|>",
|
| 100 |
"single_word": false,
|
| 101 |
"lstrip": false,
|
| 102 |
"rstrip": false,
|
| 103 |
+
"normalized": false
|
|
|
|
| 104 |
},
|
| 105 |
{
|
| 106 |
"id": 50267,
|
| 107 |
+
"special": true,
|
| 108 |
"content": "<|tr|>",
|
| 109 |
"single_word": false,
|
| 110 |
"lstrip": false,
|
| 111 |
"rstrip": false,
|
| 112 |
+
"normalized": false
|
|
|
|
| 113 |
},
|
| 114 |
{
|
| 115 |
"id": 50268,
|
| 116 |
+
"special": true,
|
| 117 |
"content": "<|pl|>",
|
| 118 |
"single_word": false,
|
| 119 |
"lstrip": false,
|
| 120 |
"rstrip": false,
|
| 121 |
+
"normalized": false
|
|
|
|
| 122 |
},
|
| 123 |
{
|
| 124 |
"id": 50269,
|
| 125 |
+
"special": true,
|
| 126 |
"content": "<|ca|>",
|
| 127 |
"single_word": false,
|
| 128 |
"lstrip": false,
|
| 129 |
"rstrip": false,
|
| 130 |
+
"normalized": false
|
|
|
|
| 131 |
},
|
| 132 |
{
|
| 133 |
"id": 50270,
|
| 134 |
+
"special": true,
|
| 135 |
"content": "<|nl|>",
|
| 136 |
"single_word": false,
|
| 137 |
"lstrip": false,
|
| 138 |
"rstrip": false,
|
| 139 |
+
"normalized": false
|
|
|
|
| 140 |
},
|
| 141 |
{
|
| 142 |
"id": 50271,
|
| 143 |
+
"special": true,
|
| 144 |
"content": "<|ar|>",
|
| 145 |
"single_word": false,
|
| 146 |
"lstrip": false,
|
| 147 |
"rstrip": false,
|
| 148 |
+
"normalized": false
|
|
|
|
| 149 |
},
|
| 150 |
{
|
| 151 |
"id": 50272,
|
| 152 |
+
"special": true,
|
| 153 |
"content": "<|sv|>",
|
| 154 |
"single_word": false,
|
| 155 |
"lstrip": false,
|
| 156 |
"rstrip": false,
|
| 157 |
+
"normalized": false
|
|
|
|
| 158 |
},
|
| 159 |
{
|
| 160 |
"id": 50273,
|
| 161 |
+
"special": true,
|
| 162 |
"content": "<|it|>",
|
| 163 |
"single_word": false,
|
| 164 |
"lstrip": false,
|
| 165 |
"rstrip": false,
|
| 166 |
+
"normalized": false
|
|
|
|
| 167 |
},
|
| 168 |
{
|
| 169 |
"id": 50274,
|
| 170 |
+
"special": true,
|
| 171 |
"content": "<|id|>",
|
| 172 |
"single_word": false,
|
| 173 |
"lstrip": false,
|
| 174 |
"rstrip": false,
|
| 175 |
+
"normalized": false
|
|
|
|
| 176 |
},
|
| 177 |
{
|
| 178 |
"id": 50275,
|
| 179 |
+
"special": true,
|
| 180 |
"content": "<|hi|>",
|
| 181 |
"single_word": false,
|
| 182 |
"lstrip": false,
|
| 183 |
"rstrip": false,
|
| 184 |
+
"normalized": false
|
|
|
|
| 185 |
},
|
| 186 |
{
|
| 187 |
"id": 50276,
|
| 188 |
+
"special": true,
|
| 189 |
"content": "<|fi|>",
|
| 190 |
"single_word": false,
|
| 191 |
"lstrip": false,
|
| 192 |
"rstrip": false,
|
| 193 |
+
"normalized": false
|
|
|
|
| 194 |
},
|
| 195 |
{
|
| 196 |
"id": 50277,
|
| 197 |
+
"special": true,
|
| 198 |
"content": "<|vi|>",
|
| 199 |
"single_word": false,
|
| 200 |
"lstrip": false,
|
| 201 |
"rstrip": false,
|
| 202 |
+
"normalized": false
|
|
|
|
| 203 |
},
|
| 204 |
{
|
| 205 |
"id": 50278,
|
| 206 |
+
"special": true,
|
| 207 |
"content": "<|iw|>",
|
| 208 |
"single_word": false,
|
| 209 |
"lstrip": false,
|
| 210 |
"rstrip": false,
|
| 211 |
+
"normalized": false
|
|
|
|
| 212 |
},
|
| 213 |
{
|
| 214 |
"id": 50279,
|
| 215 |
+
"special": true,
|
| 216 |
"content": "<|uk|>",
|
| 217 |
"single_word": false,
|
| 218 |
"lstrip": false,
|
| 219 |
"rstrip": false,
|
| 220 |
+
"normalized": false
|
|
|
|
| 221 |
},
|
| 222 |
{
|
| 223 |
"id": 50280,
|
| 224 |
+
"special": true,
|
| 225 |
"content": "<|el|>",
|
| 226 |
"single_word": false,
|
| 227 |
"lstrip": false,
|
| 228 |
"rstrip": false,
|
| 229 |
+
"normalized": false
|
|
|
|
| 230 |
},
|
| 231 |
{
|
| 232 |
"id": 50281,
|
| 233 |
+
"special": true,
|
| 234 |
"content": "<|ms|>",
|
| 235 |
"single_word": false,
|
| 236 |
"lstrip": false,
|
| 237 |
"rstrip": false,
|
| 238 |
+
"normalized": false
|
|
|
|
| 239 |
},
|
| 240 |
{
|
| 241 |
"id": 50282,
|
| 242 |
+
"special": true,
|
| 243 |
"content": "<|cs|>",
|
| 244 |
"single_word": false,
|
| 245 |
"lstrip": false,
|
| 246 |
"rstrip": false,
|
| 247 |
+
"normalized": false
|
|
|
|
| 248 |
},
|
| 249 |
{
|
| 250 |
"id": 50283,
|
| 251 |
+
"special": true,
|
| 252 |
"content": "<|ro|>",
|
| 253 |
"single_word": false,
|
| 254 |
"lstrip": false,
|
| 255 |
"rstrip": false,
|
| 256 |
+
"normalized": false
|
|
|
|
| 257 |
},
|
| 258 |
{
|
| 259 |
"id": 50284,
|
| 260 |
+
"special": true,
|
| 261 |
"content": "<|da|>",
|
| 262 |
"single_word": false,
|
| 263 |
"lstrip": false,
|
| 264 |
"rstrip": false,
|
| 265 |
+
"normalized": false
|
|
|
|
| 266 |
},
|
| 267 |
{
|
| 268 |
"id": 50285,
|
| 269 |
+
"special": true,
|
| 270 |
"content": "<|hu|>",
|
| 271 |
"single_word": false,
|
| 272 |
"lstrip": false,
|
| 273 |
"rstrip": false,
|
| 274 |
+
"normalized": false
|
|
|
|
| 275 |
},
|
| 276 |
{
|
| 277 |
"id": 50286,
|
| 278 |
+
"special": true,
|
| 279 |
"content": "<|ta|>",
|
| 280 |
"single_word": false,
|
| 281 |
"lstrip": false,
|
| 282 |
"rstrip": false,
|
| 283 |
+
"normalized": false
|
|
|
|
| 284 |
},
|
| 285 |
{
|
| 286 |
"id": 50287,
|
| 287 |
+
"special": true,
|
| 288 |
"content": "<|no|>",
|
| 289 |
"single_word": false,
|
| 290 |
"lstrip": false,
|
| 291 |
"rstrip": false,
|
| 292 |
+
"normalized": false
|
|
|
|
| 293 |
},
|
| 294 |
{
|
| 295 |
"id": 50288,
|
| 296 |
+
"special": true,
|
| 297 |
"content": "<|th|>",
|
| 298 |
"single_word": false,
|
| 299 |
"lstrip": false,
|
| 300 |
"rstrip": false,
|
| 301 |
+
"normalized": false
|
|
|
|
| 302 |
},
|
| 303 |
{
|
| 304 |
"id": 50289,
|
| 305 |
+
"special": true,
|
| 306 |
"content": "<|ur|>",
|
| 307 |
"single_word": false,
|
| 308 |
"lstrip": false,
|
| 309 |
"rstrip": false,
|
| 310 |
+
"normalized": false
|
|
|
|
| 311 |
},
|
| 312 |
{
|
| 313 |
"id": 50290,
|
| 314 |
+
"special": true,
|
| 315 |
"content": "<|hr|>",
|
| 316 |
"single_word": false,
|
| 317 |
"lstrip": false,
|
| 318 |
"rstrip": false,
|
| 319 |
+
"normalized": false
|
|
|
|
| 320 |
},
|
| 321 |
{
|
| 322 |
"id": 50291,
|
| 323 |
+
"special": true,
|
| 324 |
"content": "<|bg|>",
|
| 325 |
"single_word": false,
|
| 326 |
"lstrip": false,
|
| 327 |
"rstrip": false,
|
| 328 |
+
"normalized": false
|
|
|
|
| 329 |
},
|
| 330 |
{
|
| 331 |
"id": 50292,
|
| 332 |
+
"special": true,
|
| 333 |
"content": "<|lt|>",
|
| 334 |
"single_word": false,
|
| 335 |
"lstrip": false,
|
| 336 |
"rstrip": false,
|
| 337 |
+
"normalized": false
|
|
|
|
| 338 |
},
|
| 339 |
{
|
| 340 |
"id": 50293,
|
| 341 |
+
"special": true,
|
| 342 |
"content": "<|la|>",
|
| 343 |
"single_word": false,
|
| 344 |
"lstrip": false,
|
| 345 |
"rstrip": false,
|
| 346 |
+
"normalized": false
|
|
|
|
| 347 |
},
|
| 348 |
{
|
| 349 |
"id": 50294,
|
| 350 |
+
"special": true,
|
| 351 |
"content": "<|mi|>",
|
| 352 |
"single_word": false,
|
| 353 |
"lstrip": false,
|
| 354 |
"rstrip": false,
|
| 355 |
+
"normalized": false
|
|
|
|
| 356 |
},
|
| 357 |
{
|
| 358 |
"id": 50295,
|
| 359 |
+
"special": true,
|
| 360 |
"content": "<|ml|>",
|
| 361 |
"single_word": false,
|
| 362 |
"lstrip": false,
|
| 363 |
"rstrip": false,
|
| 364 |
+
"normalized": false
|
|
|
|
| 365 |
},
|
| 366 |
{
|
| 367 |
"id": 50296,
|
| 368 |
+
"special": true,
|
| 369 |
"content": "<|cy|>",
|
| 370 |
"single_word": false,
|
| 371 |
"lstrip": false,
|
| 372 |
"rstrip": false,
|
| 373 |
+
"normalized": false
|
|
|
|
| 374 |
},
|
| 375 |
{
|
| 376 |
"id": 50297,
|
| 377 |
+
"special": true,
|
| 378 |
"content": "<|sk|>",
|
| 379 |
"single_word": false,
|
| 380 |
"lstrip": false,
|
| 381 |
"rstrip": false,
|
| 382 |
+
"normalized": false
|
|
|
|
| 383 |
},
|
| 384 |
{
|
| 385 |
"id": 50298,
|
| 386 |
+
"special": true,
|
| 387 |
"content": "<|te|>",
|
| 388 |
"single_word": false,
|
| 389 |
"lstrip": false,
|
| 390 |
"rstrip": false,
|
| 391 |
+
"normalized": false
|
|
|
|
| 392 |
},
|
| 393 |
{
|
| 394 |
"id": 50299,
|
| 395 |
+
"special": true,
|
| 396 |
"content": "<|fa|>",
|
| 397 |
"single_word": false,
|
| 398 |
"lstrip": false,
|
| 399 |
"rstrip": false,
|
| 400 |
+
"normalized": false
|
|
|
|
| 401 |
},
|
| 402 |
{
|
| 403 |
"id": 50300,
|
| 404 |
+
"special": true,
|
| 405 |
"content": "<|lv|>",
|
| 406 |
"single_word": false,
|
| 407 |
"lstrip": false,
|
| 408 |
"rstrip": false,
|
| 409 |
+
"normalized": false
|
|
|
|
| 410 |
},
|
| 411 |
{
|
| 412 |
"id": 50301,
|
| 413 |
+
"special": true,
|
| 414 |
"content": "<|bn|>",
|
| 415 |
"single_word": false,
|
| 416 |
"lstrip": false,
|
| 417 |
"rstrip": false,
|
| 418 |
+
"normalized": false
|
|
|
|
| 419 |
},
|
| 420 |
{
|
| 421 |
"id": 50302,
|
| 422 |
+
"special": true,
|
| 423 |
"content": "<|sr|>",
|
| 424 |
"single_word": false,
|
| 425 |
"lstrip": false,
|
| 426 |
"rstrip": false,
|
| 427 |
+
"normalized": false
|
|
|
|
| 428 |
},
|
| 429 |
{
|
| 430 |
"id": 50303,
|
| 431 |
+
"special": true,
|
| 432 |
"content": "<|az|>",
|
| 433 |
"single_word": false,
|
| 434 |
"lstrip": false,
|
| 435 |
"rstrip": false,
|
| 436 |
+
"normalized": false
|
|
|
|
| 437 |
},
|
| 438 |
{
|
| 439 |
"id": 50304,
|
| 440 |
+
"special": true,
|
| 441 |
"content": "<|sl|>",
|
| 442 |
"single_word": false,
|
| 443 |
"lstrip": false,
|
| 444 |
"rstrip": false,
|
| 445 |
+
"normalized": false
|
|
|
|
| 446 |
},
|
| 447 |
{
|
| 448 |
"id": 50305,
|
| 449 |
+
"special": true,
|
| 450 |
"content": "<|kn|>",
|
| 451 |
"single_word": false,
|
| 452 |
"lstrip": false,
|
| 453 |
"rstrip": false,
|
| 454 |
+
"normalized": false
|
|
|
|
| 455 |
},
|
| 456 |
{
|
| 457 |
"id": 50306,
|
| 458 |
+
"special": true,
|
| 459 |
"content": "<|et|>",
|
| 460 |
"single_word": false,
|
| 461 |
"lstrip": false,
|
| 462 |
"rstrip": false,
|
| 463 |
+
"normalized": false
|
|
|
|
| 464 |
},
|
| 465 |
{
|
| 466 |
"id": 50307,
|
| 467 |
+
"special": true,
|
| 468 |
"content": "<|mk|>",
|
| 469 |
"single_word": false,
|
| 470 |
"lstrip": false,
|
| 471 |
"rstrip": false,
|
| 472 |
+
"normalized": false
|
|
|
|
| 473 |
},
|
| 474 |
{
|
| 475 |
"id": 50308,
|
| 476 |
+
"special": true,
|
| 477 |
"content": "<|br|>",
|
| 478 |
"single_word": false,
|
| 479 |
"lstrip": false,
|
| 480 |
"rstrip": false,
|
| 481 |
+
"normalized": false
|
|
|
|
| 482 |
},
|
| 483 |
{
|
| 484 |
"id": 50309,
|
| 485 |
+
"special": true,
|
| 486 |
"content": "<|eu|>",
|
| 487 |
"single_word": false,
|
| 488 |
"lstrip": false,
|
| 489 |
"rstrip": false,
|
| 490 |
+
"normalized": false
|
|
|
|
| 491 |
},
|
| 492 |
{
|
| 493 |
"id": 50310,
|
| 494 |
+
"special": true,
|
| 495 |
"content": "<|is|>",
|
| 496 |
"single_word": false,
|
| 497 |
"lstrip": false,
|
| 498 |
"rstrip": false,
|
| 499 |
+
"normalized": false
|
|
|
|
| 500 |
},
|
| 501 |
{
|
| 502 |
"id": 50311,
|
| 503 |
+
"special": true,
|
| 504 |
"content": "<|hy|>",
|
| 505 |
"single_word": false,
|
| 506 |
"lstrip": false,
|
| 507 |
"rstrip": false,
|
| 508 |
+
"normalized": false
|
|
|
|
| 509 |
},
|
| 510 |
{
|
| 511 |
"id": 50312,
|
| 512 |
+
"special": true,
|
| 513 |
"content": "<|ne|>",
|
| 514 |
"single_word": false,
|
| 515 |
"lstrip": false,
|
| 516 |
"rstrip": false,
|
| 517 |
+
"normalized": false
|
|
|
|
| 518 |
},
|
| 519 |
{
|
| 520 |
"id": 50313,
|
| 521 |
+
"special": true,
|
| 522 |
"content": "<|mn|>",
|
| 523 |
"single_word": false,
|
| 524 |
"lstrip": false,
|
| 525 |
"rstrip": false,
|
| 526 |
+
"normalized": false
|
|
|
|
| 527 |
},
|
| 528 |
{
|
| 529 |
"id": 50314,
|
| 530 |
+
"special": true,
|
| 531 |
"content": "<|bs|>",
|
| 532 |
"single_word": false,
|
| 533 |
"lstrip": false,
|
| 534 |
"rstrip": false,
|
| 535 |
+
"normalized": false
|
|
|
|
| 536 |
},
|
| 537 |
{
|
| 538 |
"id": 50315,
|
| 539 |
+
"special": true,
|
| 540 |
"content": "<|kk|>",
|
| 541 |
"single_word": false,
|
| 542 |
"lstrip": false,
|
| 543 |
"rstrip": false,
|
| 544 |
+
"normalized": false
|
|
|
|
| 545 |
},
|
| 546 |
{
|
| 547 |
"id": 50316,
|
| 548 |
+
"special": true,
|
| 549 |
"content": "<|sq|>",
|
| 550 |
"single_word": false,
|
| 551 |
"lstrip": false,
|
| 552 |
"rstrip": false,
|
| 553 |
+
"normalized": false
|
|
|
|
| 554 |
},
|
| 555 |
{
|
| 556 |
"id": 50317,
|
| 557 |
+
"special": true,
|
| 558 |
"content": "<|sw|>",
|
| 559 |
"single_word": false,
|
| 560 |
"lstrip": false,
|
| 561 |
"rstrip": false,
|
| 562 |
+
"normalized": false
|
|
|
|
| 563 |
},
|
| 564 |
{
|
| 565 |
"id": 50318,
|
| 566 |
+
"special": true,
|
| 567 |
"content": "<|gl|>",
|
| 568 |
"single_word": false,
|
| 569 |
"lstrip": false,
|
| 570 |
"rstrip": false,
|
| 571 |
+
"normalized": false
|
|
|
|
| 572 |
},
|
| 573 |
{
|
| 574 |
"id": 50319,
|
| 575 |
+
"special": true,
|
| 576 |
"content": "<|mr|>",
|
| 577 |
"single_word": false,
|
| 578 |
"lstrip": false,
|
| 579 |
"rstrip": false,
|
| 580 |
+
"normalized": false
|
|
|
|
| 581 |
},
|
| 582 |
{
|
| 583 |
"id": 50320,
|
| 584 |
+
"special": true,
|
| 585 |
"content": "<|pa|>",
|
| 586 |
"single_word": false,
|
| 587 |
"lstrip": false,
|
| 588 |
"rstrip": false,
|
| 589 |
+
"normalized": false
|
|
|
|
| 590 |
},
|
| 591 |
{
|
| 592 |
"id": 50321,
|
| 593 |
+
"special": true,
|
| 594 |
"content": "<|si|>",
|
| 595 |
"single_word": false,
|
| 596 |
"lstrip": false,
|
| 597 |
"rstrip": false,
|
| 598 |
+
"normalized": false
|
|
|
|
| 599 |
},
|
| 600 |
{
|
| 601 |
"id": 50322,
|
| 602 |
+
"special": true,
|
| 603 |
"content": "<|km|>",
|
| 604 |
"single_word": false,
|
| 605 |
"lstrip": false,
|
| 606 |
"rstrip": false,
|
| 607 |
+
"normalized": false
|
|
|
|
| 608 |
},
|
| 609 |
{
|
| 610 |
"id": 50323,
|
| 611 |
+
"special": true,
|
| 612 |
"content": "<|sn|>",
|
| 613 |
"single_word": false,
|
| 614 |
"lstrip": false,
|
| 615 |
"rstrip": false,
|
| 616 |
+
"normalized": false
|
|
|
|
| 617 |
},
|
| 618 |
{
|
| 619 |
"id": 50324,
|
| 620 |
+
"special": true,
|
| 621 |
"content": "<|yo|>",
|
| 622 |
"single_word": false,
|
| 623 |
"lstrip": false,
|
| 624 |
"rstrip": false,
|
| 625 |
+
"normalized": false
|
|
|
|
| 626 |
},
|
| 627 |
{
|
| 628 |
"id": 50325,
|
| 629 |
+
"special": true,
|
| 630 |
"content": "<|so|>",
|
| 631 |
"single_word": false,
|
| 632 |
"lstrip": false,
|
| 633 |
"rstrip": false,
|
| 634 |
+
"normalized": false
|
|
|
|
| 635 |
},
|
| 636 |
{
|
| 637 |
"id": 50326,
|
| 638 |
+
"special": true,
|
| 639 |
"content": "<|af|>",
|
| 640 |
"single_word": false,
|
| 641 |
"lstrip": false,
|
| 642 |
"rstrip": false,
|
| 643 |
+
"normalized": false
|
|
|
|
| 644 |
},
|
| 645 |
{
|
| 646 |
"id": 50327,
|
| 647 |
+
"special": true,
|
| 648 |
"content": "<|oc|>",
|
| 649 |
"single_word": false,
|
| 650 |
"lstrip": false,
|
| 651 |
"rstrip": false,
|
| 652 |
+
"normalized": false
|
|
|
|
| 653 |
},
|
| 654 |
{
|
| 655 |
"id": 50328,
|
| 656 |
+
"special": true,
|
| 657 |
"content": "<|ka|>",
|
| 658 |
"single_word": false,
|
| 659 |
"lstrip": false,
|
| 660 |
"rstrip": false,
|
| 661 |
+
"normalized": false
|
|
|
|
| 662 |
},
|
| 663 |
{
|
| 664 |
"id": 50329,
|
| 665 |
+
"special": true,
|
| 666 |
"content": "<|be|>",
|
| 667 |
"single_word": false,
|
| 668 |
"lstrip": false,
|
| 669 |
"rstrip": false,
|
| 670 |
+
"normalized": false
|
|
|
|
| 671 |
},
|
| 672 |
{
|
| 673 |
"id": 50330,
|
| 674 |
+
"special": true,
|
| 675 |
"content": "<|tg|>",
|
| 676 |
"single_word": false,
|
| 677 |
"lstrip": false,
|
| 678 |
"rstrip": false,
|
| 679 |
+
"normalized": false
|
|
|
|
| 680 |
},
|
| 681 |
{
|
| 682 |
"id": 50331,
|
| 683 |
+
"special": true,
|
| 684 |
"content": "<|sd|>",
|
| 685 |
"single_word": false,
|
| 686 |
"lstrip": false,
|
| 687 |
"rstrip": false,
|
| 688 |
+
"normalized": false
|
|
|
|
| 689 |
},
|
| 690 |
{
|
| 691 |
"id": 50332,
|
| 692 |
+
"special": true,
|
| 693 |
"content": "<|gu|>",
|
| 694 |
"single_word": false,
|
| 695 |
"lstrip": false,
|
| 696 |
"rstrip": false,
|
| 697 |
+
"normalized": false
|
|
|
|
| 698 |
},
|
| 699 |
{
|
| 700 |
"id": 50333,
|
| 701 |
+
"special": true,
|
| 702 |
"content": "<|am|>",
|
| 703 |
"single_word": false,
|
| 704 |
"lstrip": false,
|
| 705 |
"rstrip": false,
|
| 706 |
+
"normalized": false
|
|
|
|
| 707 |
},
|
| 708 |
{
|
| 709 |
"id": 50334,
|
| 710 |
+
"special": true,
|
| 711 |
"content": "<|yi|>",
|
| 712 |
"single_word": false,
|
| 713 |
"lstrip": false,
|
| 714 |
"rstrip": false,
|
| 715 |
+
"normalized": false
|
|
|
|
| 716 |
},
|
| 717 |
{
|
| 718 |
"id": 50335,
|
| 719 |
+
"special": true,
|
| 720 |
"content": "<|lo|>",
|
| 721 |
"single_word": false,
|
| 722 |
"lstrip": false,
|
| 723 |
"rstrip": false,
|
| 724 |
+
"normalized": false
|
|
|
|
| 725 |
},
|
| 726 |
{
|
| 727 |
"id": 50336,
|
| 728 |
+
"special": true,
|
| 729 |
"content": "<|uz|>",
|
| 730 |
"single_word": false,
|
| 731 |
"lstrip": false,
|
| 732 |
"rstrip": false,
|
| 733 |
+
"normalized": false
|
|
|
|
| 734 |
},
|
| 735 |
{
|
| 736 |
"id": 50337,
|
| 737 |
+
"special": true,
|
| 738 |
"content": "<|fo|>",
|
| 739 |
"single_word": false,
|
| 740 |
"lstrip": false,
|
| 741 |
"rstrip": false,
|
| 742 |
+
"normalized": false
|
|
|
|
| 743 |
},
|
| 744 |
{
|
| 745 |
"id": 50338,
|
| 746 |
+
"special": true,
|
| 747 |
"content": "<|ht|>",
|
| 748 |
"single_word": false,
|
| 749 |
"lstrip": false,
|
| 750 |
"rstrip": false,
|
| 751 |
+
"normalized": false
|
|
|
|
| 752 |
},
|
| 753 |
{
|
| 754 |
"id": 50339,
|
| 755 |
+
"special": true,
|
| 756 |
"content": "<|ps|>",
|
| 757 |
"single_word": false,
|
| 758 |
"lstrip": false,
|
| 759 |
"rstrip": false,
|
| 760 |
+
"normalized": false
|
|
|
|
| 761 |
},
|
| 762 |
{
|
| 763 |
"id": 50340,
|
| 764 |
+
"special": true,
|
| 765 |
"content": "<|tk|>",
|
| 766 |
"single_word": false,
|
| 767 |
"lstrip": false,
|
| 768 |
"rstrip": false,
|
| 769 |
+
"normalized": false
|
|
|
|
| 770 |
},
|
| 771 |
{
|
| 772 |
"id": 50341,
|
| 773 |
+
"special": true,
|
| 774 |
"content": "<|nn|>",
|
| 775 |
"single_word": false,
|
| 776 |
"lstrip": false,
|
| 777 |
"rstrip": false,
|
| 778 |
+
"normalized": false
|
|
|
|
| 779 |
},
|
| 780 |
{
|
| 781 |
"id": 50342,
|
| 782 |
+
"special": true,
|
| 783 |
"content": "<|mt|>",
|
| 784 |
"single_word": false,
|
| 785 |
"lstrip": false,
|
| 786 |
"rstrip": false,
|
| 787 |
+
"normalized": false
|
|
|
|
| 788 |
},
|
| 789 |
{
|
| 790 |
"id": 50343,
|
| 791 |
+
"special": true,
|
| 792 |
"content": "<|sa|>",
|
| 793 |
"single_word": false,
|
| 794 |
"lstrip": false,
|
| 795 |
"rstrip": false,
|
| 796 |
+
"normalized": false
|
|
|
|
| 797 |
},
|
| 798 |
{
|
| 799 |
"id": 50344,
|
| 800 |
+
"special": true,
|
| 801 |
"content": "<|lb|>",
|
| 802 |
"single_word": false,
|
| 803 |
"lstrip": false,
|
| 804 |
"rstrip": false,
|
| 805 |
+
"normalized": false
|
|
|
|
| 806 |
},
|
| 807 |
{
|
| 808 |
"id": 50345,
|
| 809 |
+
"special": true,
|
| 810 |
"content": "<|my|>",
|
| 811 |
"single_word": false,
|
| 812 |
"lstrip": false,
|
| 813 |
"rstrip": false,
|
| 814 |
+
"normalized": false
|
|
|
|
| 815 |
},
|
| 816 |
{
|
| 817 |
"id": 50346,
|
| 818 |
+
"special": true,
|
| 819 |
"content": "<|bo|>",
|
| 820 |
"single_word": false,
|
| 821 |
"lstrip": false,
|
| 822 |
"rstrip": false,
|
| 823 |
+
"normalized": false
|
|
|
|
| 824 |
},
|
| 825 |
{
|
| 826 |
"id": 50347,
|
| 827 |
+
"special": true,
|
| 828 |
"content": "<|tl|>",
|
| 829 |
"single_word": false,
|
| 830 |
"lstrip": false,
|
| 831 |
"rstrip": false,
|
| 832 |
+
"normalized": false
|
|
|
|
| 833 |
},
|
| 834 |
{
|
| 835 |
"id": 50348,
|
| 836 |
+
"special": true,
|
| 837 |
"content": "<|mg|>",
|
| 838 |
"single_word": false,
|
| 839 |
"lstrip": false,
|
| 840 |
"rstrip": false,
|
| 841 |
+
"normalized": false
|
|
|
|
| 842 |
},
|
| 843 |
{
|
| 844 |
"id": 50349,
|
| 845 |
+
"special": true,
|
| 846 |
"content": "<|as|>",
|
| 847 |
"single_word": false,
|
| 848 |
"lstrip": false,
|
| 849 |
"rstrip": false,
|
| 850 |
+
"normalized": false
|
|
|
|
| 851 |
},
|
| 852 |
{
|
| 853 |
"id": 50350,
|
| 854 |
+
"special": true,
|
| 855 |
"content": "<|tt|>",
|
| 856 |
"single_word": false,
|
| 857 |
"lstrip": false,
|
| 858 |
"rstrip": false,
|
| 859 |
+
"normalized": false
|
|
|
|
| 860 |
},
|
| 861 |
{
|
| 862 |
"id": 50351,
|
| 863 |
+
"special": true,
|
| 864 |
"content": "<|haw|>",
|
| 865 |
"single_word": false,
|
| 866 |
"lstrip": false,
|
| 867 |
"rstrip": false,
|
| 868 |
+
"normalized": false
|
|
|
|
| 869 |
},
|
| 870 |
{
|
| 871 |
"id": 50352,
|
| 872 |
+
"special": true,
|
| 873 |
"content": "<|ln|>",
|
| 874 |
"single_word": false,
|
| 875 |
"lstrip": false,
|
| 876 |
"rstrip": false,
|
| 877 |
+
"normalized": false
|
|
|
|
| 878 |
},
|
| 879 |
{
|
| 880 |
"id": 50353,
|
| 881 |
+
"special": true,
|
| 882 |
"content": "<|ha|>",
|
| 883 |
"single_word": false,
|
| 884 |
"lstrip": false,
|
| 885 |
"rstrip": false,
|
| 886 |
+
"normalized": false
|
|
|
|
| 887 |
},
|
| 888 |
{
|
| 889 |
"id": 50354,
|
| 890 |
+
"special": true,
|
| 891 |
"content": "<|ba|>",
|
| 892 |
"single_word": false,
|
| 893 |
"lstrip": false,
|
| 894 |
"rstrip": false,
|
| 895 |
+
"normalized": false
|
|
|
|
| 896 |
},
|
| 897 |
{
|
| 898 |
"id": 50355,
|
| 899 |
+
"special": true,
|
| 900 |
"content": "<|jw|>",
|
| 901 |
"single_word": false,
|
| 902 |
"lstrip": false,
|
| 903 |
"rstrip": false,
|
| 904 |
+
"normalized": false
|
|
|
|
| 905 |
},
|
| 906 |
{
|
| 907 |
"id": 50356,
|
| 908 |
+
"special": true,
|
| 909 |
"content": "<|su|>",
|
| 910 |
"single_word": false,
|
| 911 |
"lstrip": false,
|
| 912 |
"rstrip": false,
|
| 913 |
+
"normalized": false
|
|
|
|
| 914 |
},
|
| 915 |
{
|
| 916 |
"id": 50357,
|
| 917 |
+
"special": true,
|
| 918 |
"content": "<|translate|>",
|
| 919 |
"single_word": false,
|
| 920 |
"lstrip": false,
|
| 921 |
"rstrip": false,
|
| 922 |
+
"normalized": false
|
|
|
|
| 923 |
},
|
| 924 |
{
|
| 925 |
"id": 50358,
|
| 926 |
+
"special": true,
|
| 927 |
"content": "<|transcribe|>",
|
| 928 |
"single_word": false,
|
| 929 |
"lstrip": false,
|
| 930 |
"rstrip": false,
|
| 931 |
+
"normalized": false
|
|
|
|
| 932 |
},
|
| 933 |
{
|
| 934 |
"id": 50359,
|
| 935 |
+
"special": true,
|
| 936 |
"content": "<|startoflm|>",
|
| 937 |
"single_word": false,
|
| 938 |
"lstrip": false,
|
| 939 |
"rstrip": false,
|
| 940 |
+
"normalized": false
|
|
|
|
| 941 |
},
|
| 942 |
{
|
| 943 |
"id": 50360,
|
| 944 |
+
"special": true,
|
| 945 |
"content": "<|startofprev|>",
|
| 946 |
"single_word": false,
|
| 947 |
"lstrip": false,
|
| 948 |
"rstrip": false,
|
| 949 |
+
"normalized": false
|
|
|
|
| 950 |
},
|
| 951 |
{
|
| 952 |
"id": 50361,
|
| 953 |
+
"special": true,
|
| 954 |
"content": "<|nocaptions|>",
|
| 955 |
"single_word": false,
|
| 956 |
"lstrip": false,
|
| 957 |
"rstrip": false,
|
| 958 |
+
"normalized": false
|
|
|
|
| 959 |
},
|
| 960 |
{
|
| 961 |
"id": 50362,
|
| 962 |
+
"special": true,
|
| 963 |
"content": "<|notimestamps|>",
|
| 964 |
"single_word": false,
|
| 965 |
"lstrip": false,
|
| 966 |
"rstrip": false,
|
| 967 |
+
"normalized": false
|
|
|
|
| 968 |
}
|
| 969 |
],
|
| 970 |
"normalizer": null,
|
| 971 |
"pre_tokenizer": {
|
| 972 |
"type": "ByteLevel",
|
| 973 |
"add_prefix_space": false,
|
| 974 |
+
"trim_offsets": true
|
|
|
|
| 975 |
},
|
| 976 |
"post_processor": {
|
| 977 |
"type": "TemplateProcessing",
|
|
|
|
| 1066 |
"decoder": {
|
| 1067 |
"type": "ByteLevel",
|
| 1068 |
"add_prefix_space": true,
|
| 1069 |
+
"trim_offsets": true
|
|
|
|
| 1070 |
},
|
| 1071 |
"model": {
|
| 1072 |
"type": "BPE",
|
quantized/openai/whisper-small.en/default/tokenizer_config.json
CHANGED
|
@@ -19,7 +19,6 @@
|
|
| 19 |
},
|
| 20 |
"errors": "replace",
|
| 21 |
"model_max_length": 1024,
|
| 22 |
-
"name_or_path": "openai/whisper-small.en",
|
| 23 |
"pad_token": null,
|
| 24 |
"processor_class": "WhisperProcessor",
|
| 25 |
"return_attention_mask": false,
|
|
|
|
| 19 |
},
|
| 20 |
"errors": "replace",
|
| 21 |
"model_max_length": 1024,
|
|
|
|
| 22 |
"pad_token": null,
|
| 23 |
"processor_class": "WhisperProcessor",
|
| 24 |
"return_attention_mask": false,
|
quantized/openai/whisper-small.en/default/vocab.json
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
quantized/openai/whisper-small.en/speech2seq-lm-with-past/config.json
CHANGED
|
@@ -2,6 +2,7 @@
|
|
| 2 |
"_name_or_path": "openai/whisper-small.en",
|
| 3 |
"activation_dropout": 0.0,
|
| 4 |
"activation_function": "gelu",
|
|
|
|
| 5 |
"architectures": [
|
| 6 |
"WhisperForConditionalGeneration"
|
| 7 |
],
|
|
@@ -11,6 +12,7 @@
|
|
| 11 |
50256
|
| 12 |
],
|
| 13 |
"bos_token_id": 50257,
|
|
|
|
| 14 |
"d_model": 768,
|
| 15 |
"decoder_attention_heads": 12,
|
| 16 |
"decoder_ffn_dim": 3072,
|
|
@@ -31,6 +33,12 @@
|
|
| 31 |
],
|
| 32 |
"init_std": 0.02,
|
| 33 |
"is_encoder_decoder": true,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 34 |
"max_length": 448,
|
| 35 |
"max_source_positions": 1500,
|
| 36 |
"max_target_positions": 448,
|
|
@@ -129,7 +137,8 @@
|
|
| 129 |
50360,
|
| 130 |
50361
|
| 131 |
],
|
| 132 |
-
"transformers_version": "4.
|
| 133 |
"use_cache": true,
|
|
|
|
| 134 |
"vocab_size": 51864
|
| 135 |
}
|
|
|
|
| 2 |
"_name_or_path": "openai/whisper-small.en",
|
| 3 |
"activation_dropout": 0.0,
|
| 4 |
"activation_function": "gelu",
|
| 5 |
+
"apply_spec_augment": false,
|
| 6 |
"architectures": [
|
| 7 |
"WhisperForConditionalGeneration"
|
| 8 |
],
|
|
|
|
| 12 |
50256
|
| 13 |
],
|
| 14 |
"bos_token_id": 50257,
|
| 15 |
+
"classifier_proj_size": 256,
|
| 16 |
"d_model": 768,
|
| 17 |
"decoder_attention_heads": 12,
|
| 18 |
"decoder_ffn_dim": 3072,
|
|
|
|
| 33 |
],
|
| 34 |
"init_std": 0.02,
|
| 35 |
"is_encoder_decoder": true,
|
| 36 |
+
"mask_feature_length": 10,
|
| 37 |
+
"mask_feature_min_masks": 0,
|
| 38 |
+
"mask_feature_prob": 0.0,
|
| 39 |
+
"mask_time_length": 10,
|
| 40 |
+
"mask_time_min_masks": 2,
|
| 41 |
+
"mask_time_prob": 0.05,
|
| 42 |
"max_length": 448,
|
| 43 |
"max_source_positions": 1500,
|
| 44 |
"max_target_positions": 448,
|
|
|
|
| 137 |
50360,
|
| 138 |
50361
|
| 139 |
],
|
| 140 |
+
"transformers_version": "4.27.2",
|
| 141 |
"use_cache": true,
|
| 142 |
+
"use_weighted_layer_sum": false,
|
| 143 |
"vocab_size": 51864
|
| 144 |
}
|
quantized/openai/whisper-small.en/speech2seq-lm-with-past/decoder_model.onnx
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:65f4f9490108aed882d00c037ef6dfec10a688da713d80d17a0caf27ea81d046
|
| 3 |
+
size 196596817
|
quantized/openai/whisper-small.en/speech2seq-lm-with-past/decoder_model_merged.onnx
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f190877dc4864b3be49117d3119c0f6be5ea3b5094fe62883de7dd176ad606a8
|
| 3 |
+
size 196987486
|
quantized/openai/whisper-small.en/speech2seq-lm-with-past/decoder_with_past_model.onnx
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e9b6fc022fc14723de0769485040b034280a0685328ee3ea44f1922d2effb3bd
|
| 3 |
+
size 182188068
|
quantized/openai/whisper-small.en/speech2seq-lm-with-past/encoder_model.onnx
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f25862e6297bed816b7ec75f51b0c1f937e312e1032362b579f4cd6e1c8b4395
|
| 3 |
+
size 92704740
|
quantized/openai/whisper-small.en/speech2seq-lm-with-past/merges.txt
CHANGED
|
@@ -1,4 +1,4 @@
|
|
| 1 |
-
#version: 0.2
|
| 2 |
Ġ t
|
| 3 |
Ġ a
|
| 4 |
h e
|
|
|
|
| 1 |
+
#version: 0.2 - Trained by `huggingface/tokenizers`
|
| 2 |
Ġ t
|
| 3 |
Ġ a
|
| 4 |
h e
|
quantized/openai/whisper-small.en/speech2seq-lm-with-past/tokenizer.json
CHANGED
|
@@ -5,974 +5,973 @@
|
|
| 5 |
"added_tokens": [
|
| 6 |
{
|
| 7 |
"id": 50256,
|
|
|
|
| 8 |
"content": "<|endoftext|>",
|
| 9 |
"single_word": false,
|
| 10 |
"lstrip": false,
|
| 11 |
"rstrip": false,
|
| 12 |
-
"normalized": false
|
| 13 |
-
"special": true
|
| 14 |
},
|
| 15 |
{
|
| 16 |
"id": 50257,
|
|
|
|
| 17 |
"content": "<|startoftranscript|>",
|
| 18 |
"single_word": false,
|
| 19 |
"lstrip": false,
|
| 20 |
"rstrip": false,
|
| 21 |
-
"normalized": false
|
| 22 |
-
"special": true
|
| 23 |
},
|
| 24 |
{
|
| 25 |
"id": 50258,
|
|
|
|
| 26 |
"content": "<|en|>",
|
| 27 |
"single_word": false,
|
| 28 |
"lstrip": false,
|
| 29 |
"rstrip": false,
|
| 30 |
-
"normalized": false
|
| 31 |
-
"special": true
|
| 32 |
},
|
| 33 |
{
|
| 34 |
"id": 50259,
|
|
|
|
| 35 |
"content": "<|zh|>",
|
| 36 |
"single_word": false,
|
| 37 |
"lstrip": false,
|
| 38 |
"rstrip": false,
|
| 39 |
-
"normalized": false
|
| 40 |
-
"special": true
|
| 41 |
},
|
| 42 |
{
|
| 43 |
"id": 50260,
|
|
|
|
| 44 |
"content": "<|de|>",
|
| 45 |
"single_word": false,
|
| 46 |
"lstrip": false,
|
| 47 |
"rstrip": false,
|
| 48 |
-
"normalized": false
|
| 49 |
-
"special": true
|
| 50 |
},
|
| 51 |
{
|
| 52 |
"id": 50261,
|
|
|
|
| 53 |
"content": "<|es|>",
|
| 54 |
"single_word": false,
|
| 55 |
"lstrip": false,
|
| 56 |
"rstrip": false,
|
| 57 |
-
"normalized": false
|
| 58 |
-
"special": true
|
| 59 |
},
|
| 60 |
{
|
| 61 |
"id": 50262,
|
|
|
|
| 62 |
"content": "<|ru|>",
|
| 63 |
"single_word": false,
|
| 64 |
"lstrip": false,
|
| 65 |
"rstrip": false,
|
| 66 |
-
"normalized": false
|
| 67 |
-
"special": true
|
| 68 |
},
|
| 69 |
{
|
| 70 |
"id": 50263,
|
|
|
|
| 71 |
"content": "<|ko|>",
|
| 72 |
"single_word": false,
|
| 73 |
"lstrip": false,
|
| 74 |
"rstrip": false,
|
| 75 |
-
"normalized": false
|
| 76 |
-
"special": true
|
| 77 |
},
|
| 78 |
{
|
| 79 |
"id": 50264,
|
|
|
|
| 80 |
"content": "<|fr|>",
|
| 81 |
"single_word": false,
|
| 82 |
"lstrip": false,
|
| 83 |
"rstrip": false,
|
| 84 |
-
"normalized": false
|
| 85 |
-
"special": true
|
| 86 |
},
|
| 87 |
{
|
| 88 |
"id": 50265,
|
|
|
|
| 89 |
"content": "<|ja|>",
|
| 90 |
"single_word": false,
|
| 91 |
"lstrip": false,
|
| 92 |
"rstrip": false,
|
| 93 |
-
"normalized": false
|
| 94 |
-
"special": true
|
| 95 |
},
|
| 96 |
{
|
| 97 |
"id": 50266,
|
|
|
|
| 98 |
"content": "<|pt|>",
|
| 99 |
"single_word": false,
|
| 100 |
"lstrip": false,
|
| 101 |
"rstrip": false,
|
| 102 |
-
"normalized": false
|
| 103 |
-
"special": true
|
| 104 |
},
|
| 105 |
{
|
| 106 |
"id": 50267,
|
|
|
|
| 107 |
"content": "<|tr|>",
|
| 108 |
"single_word": false,
|
| 109 |
"lstrip": false,
|
| 110 |
"rstrip": false,
|
| 111 |
-
"normalized": false
|
| 112 |
-
"special": true
|
| 113 |
},
|
| 114 |
{
|
| 115 |
"id": 50268,
|
|
|
|
| 116 |
"content": "<|pl|>",
|
| 117 |
"single_word": false,
|
| 118 |
"lstrip": false,
|
| 119 |
"rstrip": false,
|
| 120 |
-
"normalized": false
|
| 121 |
-
"special": true
|
| 122 |
},
|
| 123 |
{
|
| 124 |
"id": 50269,
|
|
|
|
| 125 |
"content": "<|ca|>",
|
| 126 |
"single_word": false,
|
| 127 |
"lstrip": false,
|
| 128 |
"rstrip": false,
|
| 129 |
-
"normalized": false
|
| 130 |
-
"special": true
|
| 131 |
},
|
| 132 |
{
|
| 133 |
"id": 50270,
|
|
|
|
| 134 |
"content": "<|nl|>",
|
| 135 |
"single_word": false,
|
| 136 |
"lstrip": false,
|
| 137 |
"rstrip": false,
|
| 138 |
-
"normalized": false
|
| 139 |
-
"special": true
|
| 140 |
},
|
| 141 |
{
|
| 142 |
"id": 50271,
|
|
|
|
| 143 |
"content": "<|ar|>",
|
| 144 |
"single_word": false,
|
| 145 |
"lstrip": false,
|
| 146 |
"rstrip": false,
|
| 147 |
-
"normalized": false
|
| 148 |
-
"special": true
|
| 149 |
},
|
| 150 |
{
|
| 151 |
"id": 50272,
|
|
|
|
| 152 |
"content": "<|sv|>",
|
| 153 |
"single_word": false,
|
| 154 |
"lstrip": false,
|
| 155 |
"rstrip": false,
|
| 156 |
-
"normalized": false
|
| 157 |
-
"special": true
|
| 158 |
},
|
| 159 |
{
|
| 160 |
"id": 50273,
|
|
|
|
| 161 |
"content": "<|it|>",
|
| 162 |
"single_word": false,
|
| 163 |
"lstrip": false,
|
| 164 |
"rstrip": false,
|
| 165 |
-
"normalized": false
|
| 166 |
-
"special": true
|
| 167 |
},
|
| 168 |
{
|
| 169 |
"id": 50274,
|
|
|
|
| 170 |
"content": "<|id|>",
|
| 171 |
"single_word": false,
|
| 172 |
"lstrip": false,
|
| 173 |
"rstrip": false,
|
| 174 |
-
"normalized": false
|
| 175 |
-
"special": true
|
| 176 |
},
|
| 177 |
{
|
| 178 |
"id": 50275,
|
|
|
|
| 179 |
"content": "<|hi|>",
|
| 180 |
"single_word": false,
|
| 181 |
"lstrip": false,
|
| 182 |
"rstrip": false,
|
| 183 |
-
"normalized": false
|
| 184 |
-
"special": true
|
| 185 |
},
|
| 186 |
{
|
| 187 |
"id": 50276,
|
|
|
|
| 188 |
"content": "<|fi|>",
|
| 189 |
"single_word": false,
|
| 190 |
"lstrip": false,
|
| 191 |
"rstrip": false,
|
| 192 |
-
"normalized": false
|
| 193 |
-
"special": true
|
| 194 |
},
|
| 195 |
{
|
| 196 |
"id": 50277,
|
|
|
|
| 197 |
"content": "<|vi|>",
|
| 198 |
"single_word": false,
|
| 199 |
"lstrip": false,
|
| 200 |
"rstrip": false,
|
| 201 |
-
"normalized": false
|
| 202 |
-
"special": true
|
| 203 |
},
|
| 204 |
{
|
| 205 |
"id": 50278,
|
|
|
|
| 206 |
"content": "<|iw|>",
|
| 207 |
"single_word": false,
|
| 208 |
"lstrip": false,
|
| 209 |
"rstrip": false,
|
| 210 |
-
"normalized": false
|
| 211 |
-
"special": true
|
| 212 |
},
|
| 213 |
{
|
| 214 |
"id": 50279,
|
|
|
|
| 215 |
"content": "<|uk|>",
|
| 216 |
"single_word": false,
|
| 217 |
"lstrip": false,
|
| 218 |
"rstrip": false,
|
| 219 |
-
"normalized": false
|
| 220 |
-
"special": true
|
| 221 |
},
|
| 222 |
{
|
| 223 |
"id": 50280,
|
|
|
|
| 224 |
"content": "<|el|>",
|
| 225 |
"single_word": false,
|
| 226 |
"lstrip": false,
|
| 227 |
"rstrip": false,
|
| 228 |
-
"normalized": false
|
| 229 |
-
"special": true
|
| 230 |
},
|
| 231 |
{
|
| 232 |
"id": 50281,
|
|
|
|
| 233 |
"content": "<|ms|>",
|
| 234 |
"single_word": false,
|
| 235 |
"lstrip": false,
|
| 236 |
"rstrip": false,
|
| 237 |
-
"normalized": false
|
| 238 |
-
"special": true
|
| 239 |
},
|
| 240 |
{
|
| 241 |
"id": 50282,
|
|
|
|
| 242 |
"content": "<|cs|>",
|
| 243 |
"single_word": false,
|
| 244 |
"lstrip": false,
|
| 245 |
"rstrip": false,
|
| 246 |
-
"normalized": false
|
| 247 |
-
"special": true
|
| 248 |
},
|
| 249 |
{
|
| 250 |
"id": 50283,
|
|
|
|
| 251 |
"content": "<|ro|>",
|
| 252 |
"single_word": false,
|
| 253 |
"lstrip": false,
|
| 254 |
"rstrip": false,
|
| 255 |
-
"normalized": false
|
| 256 |
-
"special": true
|
| 257 |
},
|
| 258 |
{
|
| 259 |
"id": 50284,
|
|
|
|
| 260 |
"content": "<|da|>",
|
| 261 |
"single_word": false,
|
| 262 |
"lstrip": false,
|
| 263 |
"rstrip": false,
|
| 264 |
-
"normalized": false
|
| 265 |
-
"special": true
|
| 266 |
},
|
| 267 |
{
|
| 268 |
"id": 50285,
|
|
|
|
| 269 |
"content": "<|hu|>",
|
| 270 |
"single_word": false,
|
| 271 |
"lstrip": false,
|
| 272 |
"rstrip": false,
|
| 273 |
-
"normalized": false
|
| 274 |
-
"special": true
|
| 275 |
},
|
| 276 |
{
|
| 277 |
"id": 50286,
|
|
|
|
| 278 |
"content": "<|ta|>",
|
| 279 |
"single_word": false,
|
| 280 |
"lstrip": false,
|
| 281 |
"rstrip": false,
|
| 282 |
-
"normalized": false
|
| 283 |
-
"special": true
|
| 284 |
},
|
| 285 |
{
|
| 286 |
"id": 50287,
|
|
|
|
| 287 |
"content": "<|no|>",
|
| 288 |
"single_word": false,
|
| 289 |
"lstrip": false,
|
| 290 |
"rstrip": false,
|
| 291 |
-
"normalized": false
|
| 292 |
-
"special": true
|
| 293 |
},
|
| 294 |
{
|
| 295 |
"id": 50288,
|
|
|
|
| 296 |
"content": "<|th|>",
|
| 297 |
"single_word": false,
|
| 298 |
"lstrip": false,
|
| 299 |
"rstrip": false,
|
| 300 |
-
"normalized": false
|
| 301 |
-
"special": true
|
| 302 |
},
|
| 303 |
{
|
| 304 |
"id": 50289,
|
|
|
|
| 305 |
"content": "<|ur|>",
|
| 306 |
"single_word": false,
|
| 307 |
"lstrip": false,
|
| 308 |
"rstrip": false,
|
| 309 |
-
"normalized": false
|
| 310 |
-
"special": true
|
| 311 |
},
|
| 312 |
{
|
| 313 |
"id": 50290,
|
|
|
|
| 314 |
"content": "<|hr|>",
|
| 315 |
"single_word": false,
|
| 316 |
"lstrip": false,
|
| 317 |
"rstrip": false,
|
| 318 |
-
"normalized": false
|
| 319 |
-
"special": true
|
| 320 |
},
|
| 321 |
{
|
| 322 |
"id": 50291,
|
|
|
|
| 323 |
"content": "<|bg|>",
|
| 324 |
"single_word": false,
|
| 325 |
"lstrip": false,
|
| 326 |
"rstrip": false,
|
| 327 |
-
"normalized": false
|
| 328 |
-
"special": true
|
| 329 |
},
|
| 330 |
{
|
| 331 |
"id": 50292,
|
|
|
|
| 332 |
"content": "<|lt|>",
|
| 333 |
"single_word": false,
|
| 334 |
"lstrip": false,
|
| 335 |
"rstrip": false,
|
| 336 |
-
"normalized": false
|
| 337 |
-
"special": true
|
| 338 |
},
|
| 339 |
{
|
| 340 |
"id": 50293,
|
|
|
|
| 341 |
"content": "<|la|>",
|
| 342 |
"single_word": false,
|
| 343 |
"lstrip": false,
|
| 344 |
"rstrip": false,
|
| 345 |
-
"normalized": false
|
| 346 |
-
"special": true
|
| 347 |
},
|
| 348 |
{
|
| 349 |
"id": 50294,
|
|
|
|
| 350 |
"content": "<|mi|>",
|
| 351 |
"single_word": false,
|
| 352 |
"lstrip": false,
|
| 353 |
"rstrip": false,
|
| 354 |
-
"normalized": false
|
| 355 |
-
"special": true
|
| 356 |
},
|
| 357 |
{
|
| 358 |
"id": 50295,
|
|
|
|
| 359 |
"content": "<|ml|>",
|
| 360 |
"single_word": false,
|
| 361 |
"lstrip": false,
|
| 362 |
"rstrip": false,
|
| 363 |
-
"normalized": false
|
| 364 |
-
"special": true
|
| 365 |
},
|
| 366 |
{
|
| 367 |
"id": 50296,
|
|
|
|
| 368 |
"content": "<|cy|>",
|
| 369 |
"single_word": false,
|
| 370 |
"lstrip": false,
|
| 371 |
"rstrip": false,
|
| 372 |
-
"normalized": false
|
| 373 |
-
"special": true
|
| 374 |
},
|
| 375 |
{
|
| 376 |
"id": 50297,
|
|
|
|
| 377 |
"content": "<|sk|>",
|
| 378 |
"single_word": false,
|
| 379 |
"lstrip": false,
|
| 380 |
"rstrip": false,
|
| 381 |
-
"normalized": false
|
| 382 |
-
"special": true
|
| 383 |
},
|
| 384 |
{
|
| 385 |
"id": 50298,
|
|
|
|
| 386 |
"content": "<|te|>",
|
| 387 |
"single_word": false,
|
| 388 |
"lstrip": false,
|
| 389 |
"rstrip": false,
|
| 390 |
-
"normalized": false
|
| 391 |
-
"special": true
|
| 392 |
},
|
| 393 |
{
|
| 394 |
"id": 50299,
|
|
|
|
| 395 |
"content": "<|fa|>",
|
| 396 |
"single_word": false,
|
| 397 |
"lstrip": false,
|
| 398 |
"rstrip": false,
|
| 399 |
-
"normalized": false
|
| 400 |
-
"special": true
|
| 401 |
},
|
| 402 |
{
|
| 403 |
"id": 50300,
|
|
|
|
| 404 |
"content": "<|lv|>",
|
| 405 |
"single_word": false,
|
| 406 |
"lstrip": false,
|
| 407 |
"rstrip": false,
|
| 408 |
-
"normalized": false
|
| 409 |
-
"special": true
|
| 410 |
},
|
| 411 |
{
|
| 412 |
"id": 50301,
|
|
|
|
| 413 |
"content": "<|bn|>",
|
| 414 |
"single_word": false,
|
| 415 |
"lstrip": false,
|
| 416 |
"rstrip": false,
|
| 417 |
-
"normalized": false
|
| 418 |
-
"special": true
|
| 419 |
},
|
| 420 |
{
|
| 421 |
"id": 50302,
|
|
|
|
| 422 |
"content": "<|sr|>",
|
| 423 |
"single_word": false,
|
| 424 |
"lstrip": false,
|
| 425 |
"rstrip": false,
|
| 426 |
-
"normalized": false
|
| 427 |
-
"special": true
|
| 428 |
},
|
| 429 |
{
|
| 430 |
"id": 50303,
|
|
|
|
| 431 |
"content": "<|az|>",
|
| 432 |
"single_word": false,
|
| 433 |
"lstrip": false,
|
| 434 |
"rstrip": false,
|
| 435 |
-
"normalized": false
|
| 436 |
-
"special": true
|
| 437 |
},
|
| 438 |
{
|
| 439 |
"id": 50304,
|
|
|
|
| 440 |
"content": "<|sl|>",
|
| 441 |
"single_word": false,
|
| 442 |
"lstrip": false,
|
| 443 |
"rstrip": false,
|
| 444 |
-
"normalized": false
|
| 445 |
-
"special": true
|
| 446 |
},
|
| 447 |
{
|
| 448 |
"id": 50305,
|
|
|
|
| 449 |
"content": "<|kn|>",
|
| 450 |
"single_word": false,
|
| 451 |
"lstrip": false,
|
| 452 |
"rstrip": false,
|
| 453 |
-
"normalized": false
|
| 454 |
-
"special": true
|
| 455 |
},
|
| 456 |
{
|
| 457 |
"id": 50306,
|
|
|
|
| 458 |
"content": "<|et|>",
|
| 459 |
"single_word": false,
|
| 460 |
"lstrip": false,
|
| 461 |
"rstrip": false,
|
| 462 |
-
"normalized": false
|
| 463 |
-
"special": true
|
| 464 |
},
|
| 465 |
{
|
| 466 |
"id": 50307,
|
|
|
|
| 467 |
"content": "<|mk|>",
|
| 468 |
"single_word": false,
|
| 469 |
"lstrip": false,
|
| 470 |
"rstrip": false,
|
| 471 |
-
"normalized": false
|
| 472 |
-
"special": true
|
| 473 |
},
|
| 474 |
{
|
| 475 |
"id": 50308,
|
|
|
|
| 476 |
"content": "<|br|>",
|
| 477 |
"single_word": false,
|
| 478 |
"lstrip": false,
|
| 479 |
"rstrip": false,
|
| 480 |
-
"normalized": false
|
| 481 |
-
"special": true
|
| 482 |
},
|
| 483 |
{
|
| 484 |
"id": 50309,
|
|
|
|
| 485 |
"content": "<|eu|>",
|
| 486 |
"single_word": false,
|
| 487 |
"lstrip": false,
|
| 488 |
"rstrip": false,
|
| 489 |
-
"normalized": false
|
| 490 |
-
"special": true
|
| 491 |
},
|
| 492 |
{
|
| 493 |
"id": 50310,
|
|
|
|
| 494 |
"content": "<|is|>",
|
| 495 |
"single_word": false,
|
| 496 |
"lstrip": false,
|
| 497 |
"rstrip": false,
|
| 498 |
-
"normalized": false
|
| 499 |
-
"special": true
|
| 500 |
},
|
| 501 |
{
|
| 502 |
"id": 50311,
|
|
|
|
| 503 |
"content": "<|hy|>",
|
| 504 |
"single_word": false,
|
| 505 |
"lstrip": false,
|
| 506 |
"rstrip": false,
|
| 507 |
-
"normalized": false
|
| 508 |
-
"special": true
|
| 509 |
},
|
| 510 |
{
|
| 511 |
"id": 50312,
|
|
|
|
| 512 |
"content": "<|ne|>",
|
| 513 |
"single_word": false,
|
| 514 |
"lstrip": false,
|
| 515 |
"rstrip": false,
|
| 516 |
-
"normalized": false
|
| 517 |
-
"special": true
|
| 518 |
},
|
| 519 |
{
|
| 520 |
"id": 50313,
|
|
|
|
| 521 |
"content": "<|mn|>",
|
| 522 |
"single_word": false,
|
| 523 |
"lstrip": false,
|
| 524 |
"rstrip": false,
|
| 525 |
-
"normalized": false
|
| 526 |
-
"special": true
|
| 527 |
},
|
| 528 |
{
|
| 529 |
"id": 50314,
|
|
|
|
| 530 |
"content": "<|bs|>",
|
| 531 |
"single_word": false,
|
| 532 |
"lstrip": false,
|
| 533 |
"rstrip": false,
|
| 534 |
-
"normalized": false
|
| 535 |
-
"special": true
|
| 536 |
},
|
| 537 |
{
|
| 538 |
"id": 50315,
|
|
|
|
| 539 |
"content": "<|kk|>",
|
| 540 |
"single_word": false,
|
| 541 |
"lstrip": false,
|
| 542 |
"rstrip": false,
|
| 543 |
-
"normalized": false
|
| 544 |
-
"special": true
|
| 545 |
},
|
| 546 |
{
|
| 547 |
"id": 50316,
|
|
|
|
| 548 |
"content": "<|sq|>",
|
| 549 |
"single_word": false,
|
| 550 |
"lstrip": false,
|
| 551 |
"rstrip": false,
|
| 552 |
-
"normalized": false
|
| 553 |
-
"special": true
|
| 554 |
},
|
| 555 |
{
|
| 556 |
"id": 50317,
|
|
|
|
| 557 |
"content": "<|sw|>",
|
| 558 |
"single_word": false,
|
| 559 |
"lstrip": false,
|
| 560 |
"rstrip": false,
|
| 561 |
-
"normalized": false
|
| 562 |
-
"special": true
|
| 563 |
},
|
| 564 |
{
|
| 565 |
"id": 50318,
|
|
|
|
| 566 |
"content": "<|gl|>",
|
| 567 |
"single_word": false,
|
| 568 |
"lstrip": false,
|
| 569 |
"rstrip": false,
|
| 570 |
-
"normalized": false
|
| 571 |
-
"special": true
|
| 572 |
},
|
| 573 |
{
|
| 574 |
"id": 50319,
|
|
|
|
| 575 |
"content": "<|mr|>",
|
| 576 |
"single_word": false,
|
| 577 |
"lstrip": false,
|
| 578 |
"rstrip": false,
|
| 579 |
-
"normalized": false
|
| 580 |
-
"special": true
|
| 581 |
},
|
| 582 |
{
|
| 583 |
"id": 50320,
|
|
|
|
| 584 |
"content": "<|pa|>",
|
| 585 |
"single_word": false,
|
| 586 |
"lstrip": false,
|
| 587 |
"rstrip": false,
|
| 588 |
-
"normalized": false
|
| 589 |
-
"special": true
|
| 590 |
},
|
| 591 |
{
|
| 592 |
"id": 50321,
|
|
|
|
| 593 |
"content": "<|si|>",
|
| 594 |
"single_word": false,
|
| 595 |
"lstrip": false,
|
| 596 |
"rstrip": false,
|
| 597 |
-
"normalized": false
|
| 598 |
-
"special": true
|
| 599 |
},
|
| 600 |
{
|
| 601 |
"id": 50322,
|
|
|
|
| 602 |
"content": "<|km|>",
|
| 603 |
"single_word": false,
|
| 604 |
"lstrip": false,
|
| 605 |
"rstrip": false,
|
| 606 |
-
"normalized": false
|
| 607 |
-
"special": true
|
| 608 |
},
|
| 609 |
{
|
| 610 |
"id": 50323,
|
|
|
|
| 611 |
"content": "<|sn|>",
|
| 612 |
"single_word": false,
|
| 613 |
"lstrip": false,
|
| 614 |
"rstrip": false,
|
| 615 |
-
"normalized": false
|
| 616 |
-
"special": true
|
| 617 |
},
|
| 618 |
{
|
| 619 |
"id": 50324,
|
|
|
|
| 620 |
"content": "<|yo|>",
|
| 621 |
"single_word": false,
|
| 622 |
"lstrip": false,
|
| 623 |
"rstrip": false,
|
| 624 |
-
"normalized": false
|
| 625 |
-
"special": true
|
| 626 |
},
|
| 627 |
{
|
| 628 |
"id": 50325,
|
|
|
|
| 629 |
"content": "<|so|>",
|
| 630 |
"single_word": false,
|
| 631 |
"lstrip": false,
|
| 632 |
"rstrip": false,
|
| 633 |
-
"normalized": false
|
| 634 |
-
"special": true
|
| 635 |
},
|
| 636 |
{
|
| 637 |
"id": 50326,
|
|
|
|
| 638 |
"content": "<|af|>",
|
| 639 |
"single_word": false,
|
| 640 |
"lstrip": false,
|
| 641 |
"rstrip": false,
|
| 642 |
-
"normalized": false
|
| 643 |
-
"special": true
|
| 644 |
},
|
| 645 |
{
|
| 646 |
"id": 50327,
|
|
|
|
| 647 |
"content": "<|oc|>",
|
| 648 |
"single_word": false,
|
| 649 |
"lstrip": false,
|
| 650 |
"rstrip": false,
|
| 651 |
-
"normalized": false
|
| 652 |
-
"special": true
|
| 653 |
},
|
| 654 |
{
|
| 655 |
"id": 50328,
|
|
|
|
| 656 |
"content": "<|ka|>",
|
| 657 |
"single_word": false,
|
| 658 |
"lstrip": false,
|
| 659 |
"rstrip": false,
|
| 660 |
-
"normalized": false
|
| 661 |
-
"special": true
|
| 662 |
},
|
| 663 |
{
|
| 664 |
"id": 50329,
|
|
|
|
| 665 |
"content": "<|be|>",
|
| 666 |
"single_word": false,
|
| 667 |
"lstrip": false,
|
| 668 |
"rstrip": false,
|
| 669 |
-
"normalized": false
|
| 670 |
-
"special": true
|
| 671 |
},
|
| 672 |
{
|
| 673 |
"id": 50330,
|
|
|
|
| 674 |
"content": "<|tg|>",
|
| 675 |
"single_word": false,
|
| 676 |
"lstrip": false,
|
| 677 |
"rstrip": false,
|
| 678 |
-
"normalized": false
|
| 679 |
-
"special": true
|
| 680 |
},
|
| 681 |
{
|
| 682 |
"id": 50331,
|
|
|
|
| 683 |
"content": "<|sd|>",
|
| 684 |
"single_word": false,
|
| 685 |
"lstrip": false,
|
| 686 |
"rstrip": false,
|
| 687 |
-
"normalized": false
|
| 688 |
-
"special": true
|
| 689 |
},
|
| 690 |
{
|
| 691 |
"id": 50332,
|
|
|
|
| 692 |
"content": "<|gu|>",
|
| 693 |
"single_word": false,
|
| 694 |
"lstrip": false,
|
| 695 |
"rstrip": false,
|
| 696 |
-
"normalized": false
|
| 697 |
-
"special": true
|
| 698 |
},
|
| 699 |
{
|
| 700 |
"id": 50333,
|
|
|
|
| 701 |
"content": "<|am|>",
|
| 702 |
"single_word": false,
|
| 703 |
"lstrip": false,
|
| 704 |
"rstrip": false,
|
| 705 |
-
"normalized": false
|
| 706 |
-
"special": true
|
| 707 |
},
|
| 708 |
{
|
| 709 |
"id": 50334,
|
|
|
|
| 710 |
"content": "<|yi|>",
|
| 711 |
"single_word": false,
|
| 712 |
"lstrip": false,
|
| 713 |
"rstrip": false,
|
| 714 |
-
"normalized": false
|
| 715 |
-
"special": true
|
| 716 |
},
|
| 717 |
{
|
| 718 |
"id": 50335,
|
|
|
|
| 719 |
"content": "<|lo|>",
|
| 720 |
"single_word": false,
|
| 721 |
"lstrip": false,
|
| 722 |
"rstrip": false,
|
| 723 |
-
"normalized": false
|
| 724 |
-
"special": true
|
| 725 |
},
|
| 726 |
{
|
| 727 |
"id": 50336,
|
|
|
|
| 728 |
"content": "<|uz|>",
|
| 729 |
"single_word": false,
|
| 730 |
"lstrip": false,
|
| 731 |
"rstrip": false,
|
| 732 |
-
"normalized": false
|
| 733 |
-
"special": true
|
| 734 |
},
|
| 735 |
{
|
| 736 |
"id": 50337,
|
|
|
|
| 737 |
"content": "<|fo|>",
|
| 738 |
"single_word": false,
|
| 739 |
"lstrip": false,
|
| 740 |
"rstrip": false,
|
| 741 |
-
"normalized": false
|
| 742 |
-
"special": true
|
| 743 |
},
|
| 744 |
{
|
| 745 |
"id": 50338,
|
|
|
|
| 746 |
"content": "<|ht|>",
|
| 747 |
"single_word": false,
|
| 748 |
"lstrip": false,
|
| 749 |
"rstrip": false,
|
| 750 |
-
"normalized": false
|
| 751 |
-
"special": true
|
| 752 |
},
|
| 753 |
{
|
| 754 |
"id": 50339,
|
|
|
|
| 755 |
"content": "<|ps|>",
|
| 756 |
"single_word": false,
|
| 757 |
"lstrip": false,
|
| 758 |
"rstrip": false,
|
| 759 |
-
"normalized": false
|
| 760 |
-
"special": true
|
| 761 |
},
|
| 762 |
{
|
| 763 |
"id": 50340,
|
|
|
|
| 764 |
"content": "<|tk|>",
|
| 765 |
"single_word": false,
|
| 766 |
"lstrip": false,
|
| 767 |
"rstrip": false,
|
| 768 |
-
"normalized": false
|
| 769 |
-
"special": true
|
| 770 |
},
|
| 771 |
{
|
| 772 |
"id": 50341,
|
|
|
|
| 773 |
"content": "<|nn|>",
|
| 774 |
"single_word": false,
|
| 775 |
"lstrip": false,
|
| 776 |
"rstrip": false,
|
| 777 |
-
"normalized": false
|
| 778 |
-
"special": true
|
| 779 |
},
|
| 780 |
{
|
| 781 |
"id": 50342,
|
|
|
|
| 782 |
"content": "<|mt|>",
|
| 783 |
"single_word": false,
|
| 784 |
"lstrip": false,
|
| 785 |
"rstrip": false,
|
| 786 |
-
"normalized": false
|
| 787 |
-
"special": true
|
| 788 |
},
|
| 789 |
{
|
| 790 |
"id": 50343,
|
|
|
|
| 791 |
"content": "<|sa|>",
|
| 792 |
"single_word": false,
|
| 793 |
"lstrip": false,
|
| 794 |
"rstrip": false,
|
| 795 |
-
"normalized": false
|
| 796 |
-
"special": true
|
| 797 |
},
|
| 798 |
{
|
| 799 |
"id": 50344,
|
|
|
|
| 800 |
"content": "<|lb|>",
|
| 801 |
"single_word": false,
|
| 802 |
"lstrip": false,
|
| 803 |
"rstrip": false,
|
| 804 |
-
"normalized": false
|
| 805 |
-
"special": true
|
| 806 |
},
|
| 807 |
{
|
| 808 |
"id": 50345,
|
|
|
|
| 809 |
"content": "<|my|>",
|
| 810 |
"single_word": false,
|
| 811 |
"lstrip": false,
|
| 812 |
"rstrip": false,
|
| 813 |
-
"normalized": false
|
| 814 |
-
"special": true
|
| 815 |
},
|
| 816 |
{
|
| 817 |
"id": 50346,
|
|
|
|
| 818 |
"content": "<|bo|>",
|
| 819 |
"single_word": false,
|
| 820 |
"lstrip": false,
|
| 821 |
"rstrip": false,
|
| 822 |
-
"normalized": false
|
| 823 |
-
"special": true
|
| 824 |
},
|
| 825 |
{
|
| 826 |
"id": 50347,
|
|
|
|
| 827 |
"content": "<|tl|>",
|
| 828 |
"single_word": false,
|
| 829 |
"lstrip": false,
|
| 830 |
"rstrip": false,
|
| 831 |
-
"normalized": false
|
| 832 |
-
"special": true
|
| 833 |
},
|
| 834 |
{
|
| 835 |
"id": 50348,
|
|
|
|
| 836 |
"content": "<|mg|>",
|
| 837 |
"single_word": false,
|
| 838 |
"lstrip": false,
|
| 839 |
"rstrip": false,
|
| 840 |
-
"normalized": false
|
| 841 |
-
"special": true
|
| 842 |
},
|
| 843 |
{
|
| 844 |
"id": 50349,
|
|
|
|
| 845 |
"content": "<|as|>",
|
| 846 |
"single_word": false,
|
| 847 |
"lstrip": false,
|
| 848 |
"rstrip": false,
|
| 849 |
-
"normalized": false
|
| 850 |
-
"special": true
|
| 851 |
},
|
| 852 |
{
|
| 853 |
"id": 50350,
|
|
|
|
| 854 |
"content": "<|tt|>",
|
| 855 |
"single_word": false,
|
| 856 |
"lstrip": false,
|
| 857 |
"rstrip": false,
|
| 858 |
-
"normalized": false
|
| 859 |
-
"special": true
|
| 860 |
},
|
| 861 |
{
|
| 862 |
"id": 50351,
|
|
|
|
| 863 |
"content": "<|haw|>",
|
| 864 |
"single_word": false,
|
| 865 |
"lstrip": false,
|
| 866 |
"rstrip": false,
|
| 867 |
-
"normalized": false
|
| 868 |
-
"special": true
|
| 869 |
},
|
| 870 |
{
|
| 871 |
"id": 50352,
|
|
|
|
| 872 |
"content": "<|ln|>",
|
| 873 |
"single_word": false,
|
| 874 |
"lstrip": false,
|
| 875 |
"rstrip": false,
|
| 876 |
-
"normalized": false
|
| 877 |
-
"special": true
|
| 878 |
},
|
| 879 |
{
|
| 880 |
"id": 50353,
|
|
|
|
| 881 |
"content": "<|ha|>",
|
| 882 |
"single_word": false,
|
| 883 |
"lstrip": false,
|
| 884 |
"rstrip": false,
|
| 885 |
-
"normalized": false
|
| 886 |
-
"special": true
|
| 887 |
},
|
| 888 |
{
|
| 889 |
"id": 50354,
|
|
|
|
| 890 |
"content": "<|ba|>",
|
| 891 |
"single_word": false,
|
| 892 |
"lstrip": false,
|
| 893 |
"rstrip": false,
|
| 894 |
-
"normalized": false
|
| 895 |
-
"special": true
|
| 896 |
},
|
| 897 |
{
|
| 898 |
"id": 50355,
|
|
|
|
| 899 |
"content": "<|jw|>",
|
| 900 |
"single_word": false,
|
| 901 |
"lstrip": false,
|
| 902 |
"rstrip": false,
|
| 903 |
-
"normalized": false
|
| 904 |
-
"special": true
|
| 905 |
},
|
| 906 |
{
|
| 907 |
"id": 50356,
|
|
|
|
| 908 |
"content": "<|su|>",
|
| 909 |
"single_word": false,
|
| 910 |
"lstrip": false,
|
| 911 |
"rstrip": false,
|
| 912 |
-
"normalized": false
|
| 913 |
-
"special": true
|
| 914 |
},
|
| 915 |
{
|
| 916 |
"id": 50357,
|
|
|
|
| 917 |
"content": "<|translate|>",
|
| 918 |
"single_word": false,
|
| 919 |
"lstrip": false,
|
| 920 |
"rstrip": false,
|
| 921 |
-
"normalized": false
|
| 922 |
-
"special": true
|
| 923 |
},
|
| 924 |
{
|
| 925 |
"id": 50358,
|
|
|
|
| 926 |
"content": "<|transcribe|>",
|
| 927 |
"single_word": false,
|
| 928 |
"lstrip": false,
|
| 929 |
"rstrip": false,
|
| 930 |
-
"normalized": false
|
| 931 |
-
"special": true
|
| 932 |
},
|
| 933 |
{
|
| 934 |
"id": 50359,
|
|
|
|
| 935 |
"content": "<|startoflm|>",
|
| 936 |
"single_word": false,
|
| 937 |
"lstrip": false,
|
| 938 |
"rstrip": false,
|
| 939 |
-
"normalized": false
|
| 940 |
-
"special": true
|
| 941 |
},
|
| 942 |
{
|
| 943 |
"id": 50360,
|
|
|
|
| 944 |
"content": "<|startofprev|>",
|
| 945 |
"single_word": false,
|
| 946 |
"lstrip": false,
|
| 947 |
"rstrip": false,
|
| 948 |
-
"normalized": false
|
| 949 |
-
"special": true
|
| 950 |
},
|
| 951 |
{
|
| 952 |
"id": 50361,
|
|
|
|
| 953 |
"content": "<|nocaptions|>",
|
| 954 |
"single_word": false,
|
| 955 |
"lstrip": false,
|
| 956 |
"rstrip": false,
|
| 957 |
-
"normalized": false
|
| 958 |
-
"special": true
|
| 959 |
},
|
| 960 |
{
|
| 961 |
"id": 50362,
|
|
|
|
| 962 |
"content": "<|notimestamps|>",
|
| 963 |
"single_word": false,
|
| 964 |
"lstrip": false,
|
| 965 |
"rstrip": false,
|
| 966 |
-
"normalized": false
|
| 967 |
-
"special": true
|
| 968 |
}
|
| 969 |
],
|
| 970 |
"normalizer": null,
|
| 971 |
"pre_tokenizer": {
|
| 972 |
"type": "ByteLevel",
|
| 973 |
"add_prefix_space": false,
|
| 974 |
-
"trim_offsets": true
|
| 975 |
-
"use_regex": true
|
| 976 |
},
|
| 977 |
"post_processor": {
|
| 978 |
"type": "TemplateProcessing",
|
|
@@ -1067,8 +1066,7 @@
|
|
| 1067 |
"decoder": {
|
| 1068 |
"type": "ByteLevel",
|
| 1069 |
"add_prefix_space": true,
|
| 1070 |
-
"trim_offsets": true
|
| 1071 |
-
"use_regex": true
|
| 1072 |
},
|
| 1073 |
"model": {
|
| 1074 |
"type": "BPE",
|
|
|
|
| 5 |
"added_tokens": [
|
| 6 |
{
|
| 7 |
"id": 50256,
|
| 8 |
+
"special": true,
|
| 9 |
"content": "<|endoftext|>",
|
| 10 |
"single_word": false,
|
| 11 |
"lstrip": false,
|
| 12 |
"rstrip": false,
|
| 13 |
+
"normalized": false
|
|
|
|
| 14 |
},
|
| 15 |
{
|
| 16 |
"id": 50257,
|
| 17 |
+
"special": true,
|
| 18 |
"content": "<|startoftranscript|>",
|
| 19 |
"single_word": false,
|
| 20 |
"lstrip": false,
|
| 21 |
"rstrip": false,
|
| 22 |
+
"normalized": false
|
|
|
|
| 23 |
},
|
| 24 |
{
|
| 25 |
"id": 50258,
|
| 26 |
+
"special": true,
|
| 27 |
"content": "<|en|>",
|
| 28 |
"single_word": false,
|
| 29 |
"lstrip": false,
|
| 30 |
"rstrip": false,
|
| 31 |
+
"normalized": false
|
|
|
|
| 32 |
},
|
| 33 |
{
|
| 34 |
"id": 50259,
|
| 35 |
+
"special": true,
|
| 36 |
"content": "<|zh|>",
|
| 37 |
"single_word": false,
|
| 38 |
"lstrip": false,
|
| 39 |
"rstrip": false,
|
| 40 |
+
"normalized": false
|
|
|
|
| 41 |
},
|
| 42 |
{
|
| 43 |
"id": 50260,
|
| 44 |
+
"special": true,
|
| 45 |
"content": "<|de|>",
|
| 46 |
"single_word": false,
|
| 47 |
"lstrip": false,
|
| 48 |
"rstrip": false,
|
| 49 |
+
"normalized": false
|
|
|
|
| 50 |
},
|
| 51 |
{
|
| 52 |
"id": 50261,
|
| 53 |
+
"special": true,
|
| 54 |
"content": "<|es|>",
|
| 55 |
"single_word": false,
|
| 56 |
"lstrip": false,
|
| 57 |
"rstrip": false,
|
| 58 |
+
"normalized": false
|
|
|
|
| 59 |
},
|
| 60 |
{
|
| 61 |
"id": 50262,
|
| 62 |
+
"special": true,
|
| 63 |
"content": "<|ru|>",
|
| 64 |
"single_word": false,
|
| 65 |
"lstrip": false,
|
| 66 |
"rstrip": false,
|
| 67 |
+
"normalized": false
|
|
|
|
| 68 |
},
|
| 69 |
{
|
| 70 |
"id": 50263,
|
| 71 |
+
"special": true,
|
| 72 |
"content": "<|ko|>",
|
| 73 |
"single_word": false,
|
| 74 |
"lstrip": false,
|
| 75 |
"rstrip": false,
|
| 76 |
+
"normalized": false
|
|
|
|
| 77 |
},
|
| 78 |
{
|
| 79 |
"id": 50264,
|
| 80 |
+
"special": true,
|
| 81 |
"content": "<|fr|>",
|
| 82 |
"single_word": false,
|
| 83 |
"lstrip": false,
|
| 84 |
"rstrip": false,
|
| 85 |
+
"normalized": false
|
|
|
|
| 86 |
},
|
| 87 |
{
|
| 88 |
"id": 50265,
|
| 89 |
+
"special": true,
|
| 90 |
"content": "<|ja|>",
|
| 91 |
"single_word": false,
|
| 92 |
"lstrip": false,
|
| 93 |
"rstrip": false,
|
| 94 |
+
"normalized": false
|
|
|
|
| 95 |
},
|
| 96 |
{
|
| 97 |
"id": 50266,
|
| 98 |
+
"special": true,
|
| 99 |
"content": "<|pt|>",
|
| 100 |
"single_word": false,
|
| 101 |
"lstrip": false,
|
| 102 |
"rstrip": false,
|
| 103 |
+
"normalized": false
|
|
|
|
| 104 |
},
|
| 105 |
{
|
| 106 |
"id": 50267,
|
| 107 |
+
"special": true,
|
| 108 |
"content": "<|tr|>",
|
| 109 |
"single_word": false,
|
| 110 |
"lstrip": false,
|
| 111 |
"rstrip": false,
|
| 112 |
+
"normalized": false
|
|
|
|
| 113 |
},
|
| 114 |
{
|
| 115 |
"id": 50268,
|
| 116 |
+
"special": true,
|
| 117 |
"content": "<|pl|>",
|
| 118 |
"single_word": false,
|
| 119 |
"lstrip": false,
|
| 120 |
"rstrip": false,
|
| 121 |
+
"normalized": false
|
|
|
|
| 122 |
},
|
| 123 |
{
|
| 124 |
"id": 50269,
|
| 125 |
+
"special": true,
|
| 126 |
"content": "<|ca|>",
|
| 127 |
"single_word": false,
|
| 128 |
"lstrip": false,
|
| 129 |
"rstrip": false,
|
| 130 |
+
"normalized": false
|
|
|
|
| 131 |
},
|
| 132 |
{
|
| 133 |
"id": 50270,
|
| 134 |
+
"special": true,
|
| 135 |
"content": "<|nl|>",
|
| 136 |
"single_word": false,
|
| 137 |
"lstrip": false,
|
| 138 |
"rstrip": false,
|
| 139 |
+
"normalized": false
|
|
|
|
| 140 |
},
|
| 141 |
{
|
| 142 |
"id": 50271,
|
| 143 |
+
"special": true,
|
| 144 |
"content": "<|ar|>",
|
| 145 |
"single_word": false,
|
| 146 |
"lstrip": false,
|
| 147 |
"rstrip": false,
|
| 148 |
+
"normalized": false
|
|
|
|
| 149 |
},
|
| 150 |
{
|
| 151 |
"id": 50272,
|
| 152 |
+
"special": true,
|
| 153 |
"content": "<|sv|>",
|
| 154 |
"single_word": false,
|
| 155 |
"lstrip": false,
|
| 156 |
"rstrip": false,
|
| 157 |
+
"normalized": false
|
|
|
|
| 158 |
},
|
| 159 |
{
|
| 160 |
"id": 50273,
|
| 161 |
+
"special": true,
|
| 162 |
"content": "<|it|>",
|
| 163 |
"single_word": false,
|
| 164 |
"lstrip": false,
|
| 165 |
"rstrip": false,
|
| 166 |
+
"normalized": false
|
|
|
|
| 167 |
},
|
| 168 |
{
|
| 169 |
"id": 50274,
|
| 170 |
+
"special": true,
|
| 171 |
"content": "<|id|>",
|
| 172 |
"single_word": false,
|
| 173 |
"lstrip": false,
|
| 174 |
"rstrip": false,
|
| 175 |
+
"normalized": false
|
|
|
|
| 176 |
},
|
| 177 |
{
|
| 178 |
"id": 50275,
|
| 179 |
+
"special": true,
|
| 180 |
"content": "<|hi|>",
|
| 181 |
"single_word": false,
|
| 182 |
"lstrip": false,
|
| 183 |
"rstrip": false,
|
| 184 |
+
"normalized": false
|
|
|
|
| 185 |
},
|
| 186 |
{
|
| 187 |
"id": 50276,
|
| 188 |
+
"special": true,
|
| 189 |
"content": "<|fi|>",
|
| 190 |
"single_word": false,
|
| 191 |
"lstrip": false,
|
| 192 |
"rstrip": false,
|
| 193 |
+
"normalized": false
|
|
|
|
| 194 |
},
|
| 195 |
{
|
| 196 |
"id": 50277,
|
| 197 |
+
"special": true,
|
| 198 |
"content": "<|vi|>",
|
| 199 |
"single_word": false,
|
| 200 |
"lstrip": false,
|
| 201 |
"rstrip": false,
|
| 202 |
+
"normalized": false
|
|
|
|
| 203 |
},
|
| 204 |
{
|
| 205 |
"id": 50278,
|
| 206 |
+
"special": true,
|
| 207 |
"content": "<|iw|>",
|
| 208 |
"single_word": false,
|
| 209 |
"lstrip": false,
|
| 210 |
"rstrip": false,
|
| 211 |
+
"normalized": false
|
|
|
|
| 212 |
},
|
| 213 |
{
|
| 214 |
"id": 50279,
|
| 215 |
+
"special": true,
|
| 216 |
"content": "<|uk|>",
|
| 217 |
"single_word": false,
|
| 218 |
"lstrip": false,
|
| 219 |
"rstrip": false,
|
| 220 |
+
"normalized": false
|
|
|
|
| 221 |
},
|
| 222 |
{
|
| 223 |
"id": 50280,
|
| 224 |
+
"special": true,
|
| 225 |
"content": "<|el|>",
|
| 226 |
"single_word": false,
|
| 227 |
"lstrip": false,
|
| 228 |
"rstrip": false,
|
| 229 |
+
"normalized": false
|
|
|
|
| 230 |
},
|
| 231 |
{
|
| 232 |
"id": 50281,
|
| 233 |
+
"special": true,
|
| 234 |
"content": "<|ms|>",
|
| 235 |
"single_word": false,
|
| 236 |
"lstrip": false,
|
| 237 |
"rstrip": false,
|
| 238 |
+
"normalized": false
|
|
|
|
| 239 |
},
|
| 240 |
{
|
| 241 |
"id": 50282,
|
| 242 |
+
"special": true,
|
| 243 |
"content": "<|cs|>",
|
| 244 |
"single_word": false,
|
| 245 |
"lstrip": false,
|
| 246 |
"rstrip": false,
|
| 247 |
+
"normalized": false
|
|
|
|
| 248 |
},
|
| 249 |
{
|
| 250 |
"id": 50283,
|
| 251 |
+
"special": true,
|
| 252 |
"content": "<|ro|>",
|
| 253 |
"single_word": false,
|
| 254 |
"lstrip": false,
|
| 255 |
"rstrip": false,
|
| 256 |
+
"normalized": false
|
|
|
|
| 257 |
},
|
| 258 |
{
|
| 259 |
"id": 50284,
|
| 260 |
+
"special": true,
|
| 261 |
"content": "<|da|>",
|
| 262 |
"single_word": false,
|
| 263 |
"lstrip": false,
|
| 264 |
"rstrip": false,
|
| 265 |
+
"normalized": false
|
|
|
|
| 266 |
},
|
| 267 |
{
|
| 268 |
"id": 50285,
|
| 269 |
+
"special": true,
|
| 270 |
"content": "<|hu|>",
|
| 271 |
"single_word": false,
|
| 272 |
"lstrip": false,
|
| 273 |
"rstrip": false,
|
| 274 |
+
"normalized": false
|
|
|
|
| 275 |
},
|
| 276 |
{
|
| 277 |
"id": 50286,
|
| 278 |
+
"special": true,
|
| 279 |
"content": "<|ta|>",
|
| 280 |
"single_word": false,
|
| 281 |
"lstrip": false,
|
| 282 |
"rstrip": false,
|
| 283 |
+
"normalized": false
|
|
|
|
| 284 |
},
|
| 285 |
{
|
| 286 |
"id": 50287,
|
| 287 |
+
"special": true,
|
| 288 |
"content": "<|no|>",
|
| 289 |
"single_word": false,
|
| 290 |
"lstrip": false,
|
| 291 |
"rstrip": false,
|
| 292 |
+
"normalized": false
|
|
|
|
| 293 |
},
|
| 294 |
{
|
| 295 |
"id": 50288,
|
| 296 |
+
"special": true,
|
| 297 |
"content": "<|th|>",
|
| 298 |
"single_word": false,
|
| 299 |
"lstrip": false,
|
| 300 |
"rstrip": false,
|
| 301 |
+
"normalized": false
|
|
|
|
| 302 |
},
|
| 303 |
{
|
| 304 |
"id": 50289,
|
| 305 |
+
"special": true,
|
| 306 |
"content": "<|ur|>",
|
| 307 |
"single_word": false,
|
| 308 |
"lstrip": false,
|
| 309 |
"rstrip": false,
|
| 310 |
+
"normalized": false
|
|
|
|
| 311 |
},
|
| 312 |
{
|
| 313 |
"id": 50290,
|
| 314 |
+
"special": true,
|
| 315 |
"content": "<|hr|>",
|
| 316 |
"single_word": false,
|
| 317 |
"lstrip": false,
|
| 318 |
"rstrip": false,
|
| 319 |
+
"normalized": false
|
|
|
|
| 320 |
},
|
| 321 |
{
|
| 322 |
"id": 50291,
|
| 323 |
+
"special": true,
|
| 324 |
"content": "<|bg|>",
|
| 325 |
"single_word": false,
|
| 326 |
"lstrip": false,
|
| 327 |
"rstrip": false,
|
| 328 |
+
"normalized": false
|
|
|
|
| 329 |
},
|
| 330 |
{
|
| 331 |
"id": 50292,
|
| 332 |
+
"special": true,
|
| 333 |
"content": "<|lt|>",
|
| 334 |
"single_word": false,
|
| 335 |
"lstrip": false,
|
| 336 |
"rstrip": false,
|
| 337 |
+
"normalized": false
|
|
|
|
| 338 |
},
|
| 339 |
{
|
| 340 |
"id": 50293,
|
| 341 |
+
"special": true,
|
| 342 |
"content": "<|la|>",
|
| 343 |
"single_word": false,
|
| 344 |
"lstrip": false,
|
| 345 |
"rstrip": false,
|
| 346 |
+
"normalized": false
|
|
|
|
| 347 |
},
|
| 348 |
{
|
| 349 |
"id": 50294,
|
| 350 |
+
"special": true,
|
| 351 |
"content": "<|mi|>",
|
| 352 |
"single_word": false,
|
| 353 |
"lstrip": false,
|
| 354 |
"rstrip": false,
|
| 355 |
+
"normalized": false
|
|
|
|
| 356 |
},
|
| 357 |
{
|
| 358 |
"id": 50295,
|
| 359 |
+
"special": true,
|
| 360 |
"content": "<|ml|>",
|
| 361 |
"single_word": false,
|
| 362 |
"lstrip": false,
|
| 363 |
"rstrip": false,
|
| 364 |
+
"normalized": false
|
|
|
|
| 365 |
},
|
| 366 |
{
|
| 367 |
"id": 50296,
|
| 368 |
+
"special": true,
|
| 369 |
"content": "<|cy|>",
|
| 370 |
"single_word": false,
|
| 371 |
"lstrip": false,
|
| 372 |
"rstrip": false,
|
| 373 |
+
"normalized": false
|
|
|
|
| 374 |
},
|
| 375 |
{
|
| 376 |
"id": 50297,
|
| 377 |
+
"special": true,
|
| 378 |
"content": "<|sk|>",
|
| 379 |
"single_word": false,
|
| 380 |
"lstrip": false,
|
| 381 |
"rstrip": false,
|
| 382 |
+
"normalized": false
|
|
|
|
| 383 |
},
|
| 384 |
{
|
| 385 |
"id": 50298,
|
| 386 |
+
"special": true,
|
| 387 |
"content": "<|te|>",
|
| 388 |
"single_word": false,
|
| 389 |
"lstrip": false,
|
| 390 |
"rstrip": false,
|
| 391 |
+
"normalized": false
|
|
|
|
| 392 |
},
|
| 393 |
{
|
| 394 |
"id": 50299,
|
| 395 |
+
"special": true,
|
| 396 |
"content": "<|fa|>",
|
| 397 |
"single_word": false,
|
| 398 |
"lstrip": false,
|
| 399 |
"rstrip": false,
|
| 400 |
+
"normalized": false
|
|
|
|
| 401 |
},
|
| 402 |
{
|
| 403 |
"id": 50300,
|
| 404 |
+
"special": true,
|
| 405 |
"content": "<|lv|>",
|
| 406 |
"single_word": false,
|
| 407 |
"lstrip": false,
|
| 408 |
"rstrip": false,
|
| 409 |
+
"normalized": false
|
|
|
|
| 410 |
},
|
| 411 |
{
|
| 412 |
"id": 50301,
|
| 413 |
+
"special": true,
|
| 414 |
"content": "<|bn|>",
|
| 415 |
"single_word": false,
|
| 416 |
"lstrip": false,
|
| 417 |
"rstrip": false,
|
| 418 |
+
"normalized": false
|
|
|
|
| 419 |
},
|
| 420 |
{
|
| 421 |
"id": 50302,
|
| 422 |
+
"special": true,
|
| 423 |
"content": "<|sr|>",
|
| 424 |
"single_word": false,
|
| 425 |
"lstrip": false,
|
| 426 |
"rstrip": false,
|
| 427 |
+
"normalized": false
|
|
|
|
| 428 |
},
|
| 429 |
{
|
| 430 |
"id": 50303,
|
| 431 |
+
"special": true,
|
| 432 |
"content": "<|az|>",
|
| 433 |
"single_word": false,
|
| 434 |
"lstrip": false,
|
| 435 |
"rstrip": false,
|
| 436 |
+
"normalized": false
|
|
|
|
| 437 |
},
|
| 438 |
{
|
| 439 |
"id": 50304,
|
| 440 |
+
"special": true,
|
| 441 |
"content": "<|sl|>",
|
| 442 |
"single_word": false,
|
| 443 |
"lstrip": false,
|
| 444 |
"rstrip": false,
|
| 445 |
+
"normalized": false
|
|
|
|
| 446 |
},
|
| 447 |
{
|
| 448 |
"id": 50305,
|
| 449 |
+
"special": true,
|
| 450 |
"content": "<|kn|>",
|
| 451 |
"single_word": false,
|
| 452 |
"lstrip": false,
|
| 453 |
"rstrip": false,
|
| 454 |
+
"normalized": false
|
|
|
|
| 455 |
},
|
| 456 |
{
|
| 457 |
"id": 50306,
|
| 458 |
+
"special": true,
|
| 459 |
"content": "<|et|>",
|
| 460 |
"single_word": false,
|
| 461 |
"lstrip": false,
|
| 462 |
"rstrip": false,
|
| 463 |
+
"normalized": false
|
|
|
|
| 464 |
},
|
| 465 |
{
|
| 466 |
"id": 50307,
|
| 467 |
+
"special": true,
|
| 468 |
"content": "<|mk|>",
|
| 469 |
"single_word": false,
|
| 470 |
"lstrip": false,
|
| 471 |
"rstrip": false,
|
| 472 |
+
"normalized": false
|
|
|
|
| 473 |
},
|
| 474 |
{
|
| 475 |
"id": 50308,
|
| 476 |
+
"special": true,
|
| 477 |
"content": "<|br|>",
|
| 478 |
"single_word": false,
|
| 479 |
"lstrip": false,
|
| 480 |
"rstrip": false,
|
| 481 |
+
"normalized": false
|
|
|
|
| 482 |
},
|
| 483 |
{
|
| 484 |
"id": 50309,
|
| 485 |
+
"special": true,
|
| 486 |
"content": "<|eu|>",
|
| 487 |
"single_word": false,
|
| 488 |
"lstrip": false,
|
| 489 |
"rstrip": false,
|
| 490 |
+
"normalized": false
|
|
|
|
| 491 |
},
|
| 492 |
{
|
| 493 |
"id": 50310,
|
| 494 |
+
"special": true,
|
| 495 |
"content": "<|is|>",
|
| 496 |
"single_word": false,
|
| 497 |
"lstrip": false,
|
| 498 |
"rstrip": false,
|
| 499 |
+
"normalized": false
|
|
|
|
| 500 |
},
|
| 501 |
{
|
| 502 |
"id": 50311,
|
| 503 |
+
"special": true,
|
| 504 |
"content": "<|hy|>",
|
| 505 |
"single_word": false,
|
| 506 |
"lstrip": false,
|
| 507 |
"rstrip": false,
|
| 508 |
+
"normalized": false
|
|
|
|
| 509 |
},
|
| 510 |
{
|
| 511 |
"id": 50312,
|
| 512 |
+
"special": true,
|
| 513 |
"content": "<|ne|>",
|
| 514 |
"single_word": false,
|
| 515 |
"lstrip": false,
|
| 516 |
"rstrip": false,
|
| 517 |
+
"normalized": false
|
|
|
|
| 518 |
},
|
| 519 |
{
|
| 520 |
"id": 50313,
|
| 521 |
+
"special": true,
|
| 522 |
"content": "<|mn|>",
|
| 523 |
"single_word": false,
|
| 524 |
"lstrip": false,
|
| 525 |
"rstrip": false,
|
| 526 |
+
"normalized": false
|
|
|
|
| 527 |
},
|
| 528 |
{
|
| 529 |
"id": 50314,
|
| 530 |
+
"special": true,
|
| 531 |
"content": "<|bs|>",
|
| 532 |
"single_word": false,
|
| 533 |
"lstrip": false,
|
| 534 |
"rstrip": false,
|
| 535 |
+
"normalized": false
|
|
|
|
| 536 |
},
|
| 537 |
{
|
| 538 |
"id": 50315,
|
| 539 |
+
"special": true,
|
| 540 |
"content": "<|kk|>",
|
| 541 |
"single_word": false,
|
| 542 |
"lstrip": false,
|
| 543 |
"rstrip": false,
|
| 544 |
+
"normalized": false
|
|
|
|
| 545 |
},
|
| 546 |
{
|
| 547 |
"id": 50316,
|
| 548 |
+
"special": true,
|
| 549 |
"content": "<|sq|>",
|
| 550 |
"single_word": false,
|
| 551 |
"lstrip": false,
|
| 552 |
"rstrip": false,
|
| 553 |
+
"normalized": false
|
|
|
|
| 554 |
},
|
| 555 |
{
|
| 556 |
"id": 50317,
|
| 557 |
+
"special": true,
|
| 558 |
"content": "<|sw|>",
|
| 559 |
"single_word": false,
|
| 560 |
"lstrip": false,
|
| 561 |
"rstrip": false,
|
| 562 |
+
"normalized": false
|
|
|
|
| 563 |
},
|
| 564 |
{
|
| 565 |
"id": 50318,
|
| 566 |
+
"special": true,
|
| 567 |
"content": "<|gl|>",
|
| 568 |
"single_word": false,
|
| 569 |
"lstrip": false,
|
| 570 |
"rstrip": false,
|
| 571 |
+
"normalized": false
|
|
|
|
| 572 |
},
|
| 573 |
{
|
| 574 |
"id": 50319,
|
| 575 |
+
"special": true,
|
| 576 |
"content": "<|mr|>",
|
| 577 |
"single_word": false,
|
| 578 |
"lstrip": false,
|
| 579 |
"rstrip": false,
|
| 580 |
+
"normalized": false
|
|
|
|
| 581 |
},
|
| 582 |
{
|
| 583 |
"id": 50320,
|
| 584 |
+
"special": true,
|
| 585 |
"content": "<|pa|>",
|
| 586 |
"single_word": false,
|
| 587 |
"lstrip": false,
|
| 588 |
"rstrip": false,
|
| 589 |
+
"normalized": false
|
|
|
|
| 590 |
},
|
| 591 |
{
|
| 592 |
"id": 50321,
|
| 593 |
+
"special": true,
|
| 594 |
"content": "<|si|>",
|
| 595 |
"single_word": false,
|
| 596 |
"lstrip": false,
|
| 597 |
"rstrip": false,
|
| 598 |
+
"normalized": false
|
|
|
|
| 599 |
},
|
| 600 |
{
|
| 601 |
"id": 50322,
|
| 602 |
+
"special": true,
|
| 603 |
"content": "<|km|>",
|
| 604 |
"single_word": false,
|
| 605 |
"lstrip": false,
|
| 606 |
"rstrip": false,
|
| 607 |
+
"normalized": false
|
|
|
|
| 608 |
},
|
| 609 |
{
|
| 610 |
"id": 50323,
|
| 611 |
+
"special": true,
|
| 612 |
"content": "<|sn|>",
|
| 613 |
"single_word": false,
|
| 614 |
"lstrip": false,
|
| 615 |
"rstrip": false,
|
| 616 |
+
"normalized": false
|
|
|
|
| 617 |
},
|
| 618 |
{
|
| 619 |
"id": 50324,
|
| 620 |
+
"special": true,
|
| 621 |
"content": "<|yo|>",
|
| 622 |
"single_word": false,
|
| 623 |
"lstrip": false,
|
| 624 |
"rstrip": false,
|
| 625 |
+
"normalized": false
|
|
|
|
| 626 |
},
|
| 627 |
{
|
| 628 |
"id": 50325,
|
| 629 |
+
"special": true,
|
| 630 |
"content": "<|so|>",
|
| 631 |
"single_word": false,
|
| 632 |
"lstrip": false,
|
| 633 |
"rstrip": false,
|
| 634 |
+
"normalized": false
|
|
|
|
| 635 |
},
|
| 636 |
{
|
| 637 |
"id": 50326,
|
| 638 |
+
"special": true,
|
| 639 |
"content": "<|af|>",
|
| 640 |
"single_word": false,
|
| 641 |
"lstrip": false,
|
| 642 |
"rstrip": false,
|
| 643 |
+
"normalized": false
|
|
|
|
| 644 |
},
|
| 645 |
{
|
| 646 |
"id": 50327,
|
| 647 |
+
"special": true,
|
| 648 |
"content": "<|oc|>",
|
| 649 |
"single_word": false,
|
| 650 |
"lstrip": false,
|
| 651 |
"rstrip": false,
|
| 652 |
+
"normalized": false
|
|
|
|
| 653 |
},
|
| 654 |
{
|
| 655 |
"id": 50328,
|
| 656 |
+
"special": true,
|
| 657 |
"content": "<|ka|>",
|
| 658 |
"single_word": false,
|
| 659 |
"lstrip": false,
|
| 660 |
"rstrip": false,
|
| 661 |
+
"normalized": false
|
|
|
|
| 662 |
},
|
| 663 |
{
|
| 664 |
"id": 50329,
|
| 665 |
+
"special": true,
|
| 666 |
"content": "<|be|>",
|
| 667 |
"single_word": false,
|
| 668 |
"lstrip": false,
|
| 669 |
"rstrip": false,
|
| 670 |
+
"normalized": false
|
|
|
|
| 671 |
},
|
| 672 |
{
|
| 673 |
"id": 50330,
|
| 674 |
+
"special": true,
|
| 675 |
"content": "<|tg|>",
|
| 676 |
"single_word": false,
|
| 677 |
"lstrip": false,
|
| 678 |
"rstrip": false,
|
| 679 |
+
"normalized": false
|
|
|
|
| 680 |
},
|
| 681 |
{
|
| 682 |
"id": 50331,
|
| 683 |
+
"special": true,
|
| 684 |
"content": "<|sd|>",
|
| 685 |
"single_word": false,
|
| 686 |
"lstrip": false,
|
| 687 |
"rstrip": false,
|
| 688 |
+
"normalized": false
|
|
|
|
| 689 |
},
|
| 690 |
{
|
| 691 |
"id": 50332,
|
| 692 |
+
"special": true,
|
| 693 |
"content": "<|gu|>",
|
| 694 |
"single_word": false,
|
| 695 |
"lstrip": false,
|
| 696 |
"rstrip": false,
|
| 697 |
+
"normalized": false
|
|
|
|
| 698 |
},
|
| 699 |
{
|
| 700 |
"id": 50333,
|
| 701 |
+
"special": true,
|
| 702 |
"content": "<|am|>",
|
| 703 |
"single_word": false,
|
| 704 |
"lstrip": false,
|
| 705 |
"rstrip": false,
|
| 706 |
+
"normalized": false
|
|
|
|
| 707 |
},
|
| 708 |
{
|
| 709 |
"id": 50334,
|
| 710 |
+
"special": true,
|
| 711 |
"content": "<|yi|>",
|
| 712 |
"single_word": false,
|
| 713 |
"lstrip": false,
|
| 714 |
"rstrip": false,
|
| 715 |
+
"normalized": false
|
|
|
|
| 716 |
},
|
| 717 |
{
|
| 718 |
"id": 50335,
|
| 719 |
+
"special": true,
|
| 720 |
"content": "<|lo|>",
|
| 721 |
"single_word": false,
|
| 722 |
"lstrip": false,
|
| 723 |
"rstrip": false,
|
| 724 |
+
"normalized": false
|
|
|
|
| 725 |
},
|
| 726 |
{
|
| 727 |
"id": 50336,
|
| 728 |
+
"special": true,
|
| 729 |
"content": "<|uz|>",
|
| 730 |
"single_word": false,
|
| 731 |
"lstrip": false,
|
| 732 |
"rstrip": false,
|
| 733 |
+
"normalized": false
|
|
|
|
| 734 |
},
|
| 735 |
{
|
| 736 |
"id": 50337,
|
| 737 |
+
"special": true,
|
| 738 |
"content": "<|fo|>",
|
| 739 |
"single_word": false,
|
| 740 |
"lstrip": false,
|
| 741 |
"rstrip": false,
|
| 742 |
+
"normalized": false
|
|
|
|
| 743 |
},
|
| 744 |
{
|
| 745 |
"id": 50338,
|
| 746 |
+
"special": true,
|
| 747 |
"content": "<|ht|>",
|
| 748 |
"single_word": false,
|
| 749 |
"lstrip": false,
|
| 750 |
"rstrip": false,
|
| 751 |
+
"normalized": false
|
|
|
|
| 752 |
},
|
| 753 |
{
|
| 754 |
"id": 50339,
|
| 755 |
+
"special": true,
|
| 756 |
"content": "<|ps|>",
|
| 757 |
"single_word": false,
|
| 758 |
"lstrip": false,
|
| 759 |
"rstrip": false,
|
| 760 |
+
"normalized": false
|
|
|
|
| 761 |
},
|
| 762 |
{
|
| 763 |
"id": 50340,
|
| 764 |
+
"special": true,
|
| 765 |
"content": "<|tk|>",
|
| 766 |
"single_word": false,
|
| 767 |
"lstrip": false,
|
| 768 |
"rstrip": false,
|
| 769 |
+
"normalized": false
|
|
|
|
| 770 |
},
|
| 771 |
{
|
| 772 |
"id": 50341,
|
| 773 |
+
"special": true,
|
| 774 |
"content": "<|nn|>",
|
| 775 |
"single_word": false,
|
| 776 |
"lstrip": false,
|
| 777 |
"rstrip": false,
|
| 778 |
+
"normalized": false
|
|
|
|
| 779 |
},
|
| 780 |
{
|
| 781 |
"id": 50342,
|
| 782 |
+
"special": true,
|
| 783 |
"content": "<|mt|>",
|
| 784 |
"single_word": false,
|
| 785 |
"lstrip": false,
|
| 786 |
"rstrip": false,
|
| 787 |
+
"normalized": false
|
|
|
|
| 788 |
},
|
| 789 |
{
|
| 790 |
"id": 50343,
|
| 791 |
+
"special": true,
|
| 792 |
"content": "<|sa|>",
|
| 793 |
"single_word": false,
|
| 794 |
"lstrip": false,
|
| 795 |
"rstrip": false,
|
| 796 |
+
"normalized": false
|
|
|
|
| 797 |
},
|
| 798 |
{
|
| 799 |
"id": 50344,
|
| 800 |
+
"special": true,
|
| 801 |
"content": "<|lb|>",
|
| 802 |
"single_word": false,
|
| 803 |
"lstrip": false,
|
| 804 |
"rstrip": false,
|
| 805 |
+
"normalized": false
|
|
|
|
| 806 |
},
|
| 807 |
{
|
| 808 |
"id": 50345,
|
| 809 |
+
"special": true,
|
| 810 |
"content": "<|my|>",
|
| 811 |
"single_word": false,
|
| 812 |
"lstrip": false,
|
| 813 |
"rstrip": false,
|
| 814 |
+
"normalized": false
|
|
|
|
| 815 |
},
|
| 816 |
{
|
| 817 |
"id": 50346,
|
| 818 |
+
"special": true,
|
| 819 |
"content": "<|bo|>",
|
| 820 |
"single_word": false,
|
| 821 |
"lstrip": false,
|
| 822 |
"rstrip": false,
|
| 823 |
+
"normalized": false
|
|
|
|
| 824 |
},
|
| 825 |
{
|
| 826 |
"id": 50347,
|
| 827 |
+
"special": true,
|
| 828 |
"content": "<|tl|>",
|
| 829 |
"single_word": false,
|
| 830 |
"lstrip": false,
|
| 831 |
"rstrip": false,
|
| 832 |
+
"normalized": false
|
|
|
|
| 833 |
},
|
| 834 |
{
|
| 835 |
"id": 50348,
|
| 836 |
+
"special": true,
|
| 837 |
"content": "<|mg|>",
|
| 838 |
"single_word": false,
|
| 839 |
"lstrip": false,
|
| 840 |
"rstrip": false,
|
| 841 |
+
"normalized": false
|
|
|
|
| 842 |
},
|
| 843 |
{
|
| 844 |
"id": 50349,
|
| 845 |
+
"special": true,
|
| 846 |
"content": "<|as|>",
|
| 847 |
"single_word": false,
|
| 848 |
"lstrip": false,
|
| 849 |
"rstrip": false,
|
| 850 |
+
"normalized": false
|
|
|
|
| 851 |
},
|
| 852 |
{
|
| 853 |
"id": 50350,
|
| 854 |
+
"special": true,
|
| 855 |
"content": "<|tt|>",
|
| 856 |
"single_word": false,
|
| 857 |
"lstrip": false,
|
| 858 |
"rstrip": false,
|
| 859 |
+
"normalized": false
|
|
|
|
| 860 |
},
|
| 861 |
{
|
| 862 |
"id": 50351,
|
| 863 |
+
"special": true,
|
| 864 |
"content": "<|haw|>",
|
| 865 |
"single_word": false,
|
| 866 |
"lstrip": false,
|
| 867 |
"rstrip": false,
|
| 868 |
+
"normalized": false
|
|
|
|
| 869 |
},
|
| 870 |
{
|
| 871 |
"id": 50352,
|
| 872 |
+
"special": true,
|
| 873 |
"content": "<|ln|>",
|
| 874 |
"single_word": false,
|
| 875 |
"lstrip": false,
|
| 876 |
"rstrip": false,
|
| 877 |
+
"normalized": false
|
|
|
|
| 878 |
},
|
| 879 |
{
|
| 880 |
"id": 50353,
|
| 881 |
+
"special": true,
|
| 882 |
"content": "<|ha|>",
|
| 883 |
"single_word": false,
|
| 884 |
"lstrip": false,
|
| 885 |
"rstrip": false,
|
| 886 |
+
"normalized": false
|
|
|
|
| 887 |
},
|
| 888 |
{
|
| 889 |
"id": 50354,
|
| 890 |
+
"special": true,
|
| 891 |
"content": "<|ba|>",
|
| 892 |
"single_word": false,
|
| 893 |
"lstrip": false,
|
| 894 |
"rstrip": false,
|
| 895 |
+
"normalized": false
|
|
|
|
| 896 |
},
|
| 897 |
{
|
| 898 |
"id": 50355,
|
| 899 |
+
"special": true,
|
| 900 |
"content": "<|jw|>",
|
| 901 |
"single_word": false,
|
| 902 |
"lstrip": false,
|
| 903 |
"rstrip": false,
|
| 904 |
+
"normalized": false
|
|
|
|
| 905 |
},
|
| 906 |
{
|
| 907 |
"id": 50356,
|
| 908 |
+
"special": true,
|
| 909 |
"content": "<|su|>",
|
| 910 |
"single_word": false,
|
| 911 |
"lstrip": false,
|
| 912 |
"rstrip": false,
|
| 913 |
+
"normalized": false
|
|
|
|
| 914 |
},
|
| 915 |
{
|
| 916 |
"id": 50357,
|
| 917 |
+
"special": true,
|
| 918 |
"content": "<|translate|>",
|
| 919 |
"single_word": false,
|
| 920 |
"lstrip": false,
|
| 921 |
"rstrip": false,
|
| 922 |
+
"normalized": false
|
|
|
|
| 923 |
},
|
| 924 |
{
|
| 925 |
"id": 50358,
|
| 926 |
+
"special": true,
|
| 927 |
"content": "<|transcribe|>",
|
| 928 |
"single_word": false,
|
| 929 |
"lstrip": false,
|
| 930 |
"rstrip": false,
|
| 931 |
+
"normalized": false
|
|
|
|
| 932 |
},
|
| 933 |
{
|
| 934 |
"id": 50359,
|
| 935 |
+
"special": true,
|
| 936 |
"content": "<|startoflm|>",
|
| 937 |
"single_word": false,
|
| 938 |
"lstrip": false,
|
| 939 |
"rstrip": false,
|
| 940 |
+
"normalized": false
|
|
|
|
| 941 |
},
|
| 942 |
{
|
| 943 |
"id": 50360,
|
| 944 |
+
"special": true,
|
| 945 |
"content": "<|startofprev|>",
|
| 946 |
"single_word": false,
|
| 947 |
"lstrip": false,
|
| 948 |
"rstrip": false,
|
| 949 |
+
"normalized": false
|
|
|
|
| 950 |
},
|
| 951 |
{
|
| 952 |
"id": 50361,
|
| 953 |
+
"special": true,
|
| 954 |
"content": "<|nocaptions|>",
|
| 955 |
"single_word": false,
|
| 956 |
"lstrip": false,
|
| 957 |
"rstrip": false,
|
| 958 |
+
"normalized": false
|
|
|
|
| 959 |
},
|
| 960 |
{
|
| 961 |
"id": 50362,
|
| 962 |
+
"special": true,
|
| 963 |
"content": "<|notimestamps|>",
|
| 964 |
"single_word": false,
|
| 965 |
"lstrip": false,
|
| 966 |
"rstrip": false,
|
| 967 |
+
"normalized": false
|
|
|
|
| 968 |
}
|
| 969 |
],
|
| 970 |
"normalizer": null,
|
| 971 |
"pre_tokenizer": {
|
| 972 |
"type": "ByteLevel",
|
| 973 |
"add_prefix_space": false,
|
| 974 |
+
"trim_offsets": true
|
|
|
|
| 975 |
},
|
| 976 |
"post_processor": {
|
| 977 |
"type": "TemplateProcessing",
|
|
|
|
| 1066 |
"decoder": {
|
| 1067 |
"type": "ByteLevel",
|
| 1068 |
"add_prefix_space": true,
|
| 1069 |
+
"trim_offsets": true
|
|
|
|
| 1070 |
},
|
| 1071 |
"model": {
|
| 1072 |
"type": "BPE",
|
quantized/openai/whisper-small.en/speech2seq-lm-with-past/tokenizer_config.json
CHANGED
|
@@ -19,7 +19,6 @@
|
|
| 19 |
},
|
| 20 |
"errors": "replace",
|
| 21 |
"model_max_length": 1024,
|
| 22 |
-
"name_or_path": "openai/whisper-small.en",
|
| 23 |
"pad_token": null,
|
| 24 |
"processor_class": "WhisperProcessor",
|
| 25 |
"return_attention_mask": false,
|
|
|
|
| 19 |
},
|
| 20 |
"errors": "replace",
|
| 21 |
"model_max_length": 1024,
|
|
|
|
| 22 |
"pad_token": null,
|
| 23 |
"processor_class": "WhisperProcessor",
|
| 24 |
"return_attention_mask": false,
|
quantized/openai/whisper-small.en/speech2seq-lm-with-past/vocab.json
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|