Upload folder using huggingface_hub
Browse files- config.json +94 -0
- model.safetensors +3 -0
- special_tokens_map.json +6 -0
- tokenizer.json +0 -0
- tokenizer_config.json +36 -0
config.json
ADDED
|
@@ -0,0 +1,94 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"encoder_config": {
|
| 3 |
+
"model_type": "zipformer",
|
| 4 |
+
"feature_dim": 80,
|
| 5 |
+
"output_downsampling_factor": 2,
|
| 6 |
+
"num_encoder_layers": [
|
| 7 |
+
2,
|
| 8 |
+
2,
|
| 9 |
+
4,
|
| 10 |
+
5,
|
| 11 |
+
4,
|
| 12 |
+
2
|
| 13 |
+
],
|
| 14 |
+
"downsampling_factor": [
|
| 15 |
+
1,
|
| 16 |
+
2,
|
| 17 |
+
4,
|
| 18 |
+
8,
|
| 19 |
+
4,
|
| 20 |
+
2
|
| 21 |
+
],
|
| 22 |
+
"encoder_dim": [
|
| 23 |
+
192,
|
| 24 |
+
256,
|
| 25 |
+
320,
|
| 26 |
+
512,
|
| 27 |
+
320,
|
| 28 |
+
256
|
| 29 |
+
],
|
| 30 |
+
"feedforward_dim": [
|
| 31 |
+
512,
|
| 32 |
+
1024,
|
| 33 |
+
2048,
|
| 34 |
+
3072,
|
| 35 |
+
2048,
|
| 36 |
+
1024
|
| 37 |
+
],
|
| 38 |
+
"warmup_batches": 4000.0,
|
| 39 |
+
"dropout": null,
|
| 40 |
+
"num_heads": [
|
| 41 |
+
4,
|
| 42 |
+
4,
|
| 43 |
+
4,
|
| 44 |
+
8,
|
| 45 |
+
4,
|
| 46 |
+
4
|
| 47 |
+
],
|
| 48 |
+
"query_head_dim": [
|
| 49 |
+
32
|
| 50 |
+
],
|
| 51 |
+
"value_head_dim": [
|
| 52 |
+
12
|
| 53 |
+
],
|
| 54 |
+
"pos_head_dim": [
|
| 55 |
+
4
|
| 56 |
+
],
|
| 57 |
+
"pos_dim": 48,
|
| 58 |
+
"encoder_unmasked_dim": [
|
| 59 |
+
192,
|
| 60 |
+
192,
|
| 61 |
+
256,
|
| 62 |
+
256,
|
| 63 |
+
256,
|
| 64 |
+
192
|
| 65 |
+
],
|
| 66 |
+
"cnn_module_kernel": [
|
| 67 |
+
31,
|
| 68 |
+
31,
|
| 69 |
+
15,
|
| 70 |
+
15,
|
| 71 |
+
15,
|
| 72 |
+
31
|
| 73 |
+
],
|
| 74 |
+
"causal": true,
|
| 75 |
+
"chunk_size": [
|
| 76 |
+
16,
|
| 77 |
+
32,
|
| 78 |
+
64,
|
| 79 |
+
-1
|
| 80 |
+
],
|
| 81 |
+
"left_context_frames": [
|
| 82 |
+
64,
|
| 83 |
+
128,
|
| 84 |
+
256,
|
| 85 |
+
-1
|
| 86 |
+
]
|
| 87 |
+
},
|
| 88 |
+
"model_type": "asr",
|
| 89 |
+
"decoder_dim": 512,
|
| 90 |
+
"context_size": 2,
|
| 91 |
+
"joiner_dim": 512,
|
| 92 |
+
"use_transducer": true,
|
| 93 |
+
"use_ctc": false
|
| 94 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a4334d4c5b16493390526111335a1eaa275a861b869cd6625cdc23c4bf7e9320
|
| 3 |
+
size 475745708
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": "<sos/eos>",
|
| 3 |
+
"eos_token": "<sos/eos>",
|
| 4 |
+
"pad_token": "<blk>",
|
| 5 |
+
"unk_token": "<unk>"
|
| 6 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "<blk>",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"1": {
|
| 12 |
+
"content": "<sos/eos>",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"2": {
|
| 20 |
+
"content": "<unk>",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
}
|
| 27 |
+
},
|
| 28 |
+
"bos_token": "<sos/eos>",
|
| 29 |
+
"clean_up_tokenization_spaces": false,
|
| 30 |
+
"eos_token": "<sos/eos>",
|
| 31 |
+
"extra_special_tokens": {},
|
| 32 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 33 |
+
"pad_token": "<blk>",
|
| 34 |
+
"tokenizer_class": "PreTrainedTokenizer",
|
| 35 |
+
"unk_token": "<unk>"
|
| 36 |
+
}
|