Upload model conversion
Browse files- config.json +116 -0
- onnx/model.onnx +3 -0
- preprocessor_config.json +10 -0
- special_tokens_map.json +30 -0
- tokenizer.json +95 -0
- tokenizer_config.json +49 -0
- vocab.json +43 -0
config.json
ADDED
|
@@ -0,0 +1,116 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"activation_dropout": 0.0,
|
| 3 |
+
"adapter_attn_dim": null,
|
| 4 |
+
"adapter_kernel_size": 3,
|
| 5 |
+
"adapter_stride": 2,
|
| 6 |
+
"add_adapter": false,
|
| 7 |
+
"apply_spec_augment": true,
|
| 8 |
+
"architectures": [
|
| 9 |
+
"Wav2Vec2ForCTC"
|
| 10 |
+
],
|
| 11 |
+
"attention_dropout": 0.1,
|
| 12 |
+
"bos_token_id": 1,
|
| 13 |
+
"classifier_proj_size": 256,
|
| 14 |
+
"codevector_dim": 768,
|
| 15 |
+
"contrastive_logits_temperature": 0.1,
|
| 16 |
+
"conv_bias": true,
|
| 17 |
+
"conv_dim": [
|
| 18 |
+
512,
|
| 19 |
+
512,
|
| 20 |
+
512,
|
| 21 |
+
512,
|
| 22 |
+
512,
|
| 23 |
+
512,
|
| 24 |
+
512
|
| 25 |
+
],
|
| 26 |
+
"conv_kernel": [
|
| 27 |
+
10,
|
| 28 |
+
3,
|
| 29 |
+
3,
|
| 30 |
+
3,
|
| 31 |
+
3,
|
| 32 |
+
2,
|
| 33 |
+
2
|
| 34 |
+
],
|
| 35 |
+
"conv_stride": [
|
| 36 |
+
5,
|
| 37 |
+
2,
|
| 38 |
+
2,
|
| 39 |
+
2,
|
| 40 |
+
2,
|
| 41 |
+
2,
|
| 42 |
+
2
|
| 43 |
+
],
|
| 44 |
+
"ctc_loss_reduction": "mean",
|
| 45 |
+
"ctc_zero_infinity": true,
|
| 46 |
+
"diversity_loss_weight": 0.1,
|
| 47 |
+
"do_stable_layer_norm": true,
|
| 48 |
+
"eos_token_id": 2,
|
| 49 |
+
"feat_extract_activation": "gelu",
|
| 50 |
+
"feat_extract_dropout": 0.0,
|
| 51 |
+
"feat_extract_norm": "layer",
|
| 52 |
+
"feat_proj_dropout": 0.0,
|
| 53 |
+
"feat_quantizer_dropout": 0.0,
|
| 54 |
+
"final_dropout": 0.0,
|
| 55 |
+
"gradient_checkpointing": false,
|
| 56 |
+
"hidden_act": "gelu",
|
| 57 |
+
"hidden_dropout": 0.1,
|
| 58 |
+
"hidden_size": 1024,
|
| 59 |
+
"initializer_range": 0.02,
|
| 60 |
+
"intermediate_size": 4096,
|
| 61 |
+
"layer_norm_eps": 1e-05,
|
| 62 |
+
"layerdrop": 0.1,
|
| 63 |
+
"mask_channel_length": 10,
|
| 64 |
+
"mask_channel_min_space": 1,
|
| 65 |
+
"mask_channel_other": 0.0,
|
| 66 |
+
"mask_channel_prob": 0.0,
|
| 67 |
+
"mask_channel_selection": "static",
|
| 68 |
+
"mask_feature_length": 10,
|
| 69 |
+
"mask_feature_min_masks": 0,
|
| 70 |
+
"mask_feature_prob": 0.0,
|
| 71 |
+
"mask_time_length": 4,
|
| 72 |
+
"mask_time_min_masks": 2,
|
| 73 |
+
"mask_time_min_space": 1,
|
| 74 |
+
"mask_time_other": 0.0,
|
| 75 |
+
"mask_time_prob": 0.05,
|
| 76 |
+
"mask_time_selection": "static",
|
| 77 |
+
"model_type": "wav2vec2",
|
| 78 |
+
"num_adapter_layers": 3,
|
| 79 |
+
"num_attention_heads": 16,
|
| 80 |
+
"num_codevector_groups": 2,
|
| 81 |
+
"num_codevectors_per_group": 320,
|
| 82 |
+
"num_conv_pos_embedding_groups": 16,
|
| 83 |
+
"num_conv_pos_embeddings": 128,
|
| 84 |
+
"num_feat_extract_layers": 7,
|
| 85 |
+
"num_hidden_layers": 24,
|
| 86 |
+
"num_negatives": 100,
|
| 87 |
+
"output_hidden_size": 1024,
|
| 88 |
+
"pad_token_id": 0,
|
| 89 |
+
"proj_codevector_dim": 768,
|
| 90 |
+
"tdnn_dilation": [
|
| 91 |
+
1,
|
| 92 |
+
2,
|
| 93 |
+
3,
|
| 94 |
+
1,
|
| 95 |
+
1
|
| 96 |
+
],
|
| 97 |
+
"tdnn_dim": [
|
| 98 |
+
512,
|
| 99 |
+
512,
|
| 100 |
+
512,
|
| 101 |
+
512,
|
| 102 |
+
1500
|
| 103 |
+
],
|
| 104 |
+
"tdnn_kernel": [
|
| 105 |
+
5,
|
| 106 |
+
3,
|
| 107 |
+
3,
|
| 108 |
+
1,
|
| 109 |
+
1
|
| 110 |
+
],
|
| 111 |
+
"torch_dtype": "float32",
|
| 112 |
+
"transformers_version": "4.54.0",
|
| 113 |
+
"use_weighted_layer_sum": false,
|
| 114 |
+
"vocab_size": 41,
|
| 115 |
+
"xvector_output_dim": 512
|
| 116 |
+
}
|
onnx/model.onnx
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0f105dbad6a3d4cc14ac827b5cfc3947004ed24c620763f349c85cf908d42b0d
|
| 3 |
+
size 1262429429
|
preprocessor_config.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"do_normalize": true,
|
| 3 |
+
"feature_extractor_type": "Wav2Vec2FeatureExtractor",
|
| 4 |
+
"feature_size": 1,
|
| 5 |
+
"padding_side": "right",
|
| 6 |
+
"padding_value": 0.0,
|
| 7 |
+
"processor_class": "Wav2Vec2Processor",
|
| 8 |
+
"return_attention_mask": true,
|
| 9 |
+
"sampling_rate": 16000
|
| 10 |
+
}
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 4 |
+
"lstrip": true,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": true,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "</s>",
|
| 11 |
+
"lstrip": true,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": true,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": {
|
| 17 |
+
"content": "<pad>",
|
| 18 |
+
"lstrip": true,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": true,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"unk_token": {
|
| 24 |
+
"content": "<unk>",
|
| 25 |
+
"lstrip": true,
|
| 26 |
+
"normalized": false,
|
| 27 |
+
"rstrip": true,
|
| 28 |
+
"single_word": false
|
| 29 |
+
}
|
| 30 |
+
}
|
tokenizer.json
ADDED
|
@@ -0,0 +1,95 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"tokenizer_class": "Wav2Vec2CTCTokenizer",
|
| 3 |
+
"processor_class": "Wav2Vec2Processor",
|
| 4 |
+
"vocab": {
|
| 5 |
+
"</s>": 2,
|
| 6 |
+
"<pad>": 0,
|
| 7 |
+
"<s>": 1,
|
| 8 |
+
"<unk>": 3,
|
| 9 |
+
"a": 4,
|
| 10 |
+
"b": 5,
|
| 11 |
+
"d": 6,
|
| 12 |
+
"e": 7,
|
| 13 |
+
"f": 8,
|
| 14 |
+
"h": 9,
|
| 15 |
+
"i": 10,
|
| 16 |
+
"j": 11,
|
| 17 |
+
"k": 12,
|
| 18 |
+
"l": 13,
|
| 19 |
+
"m": 14,
|
| 20 |
+
"n": 15,
|
| 21 |
+
"o": 16,
|
| 22 |
+
"p": 17,
|
| 23 |
+
"s": 18,
|
| 24 |
+
"t": 19,
|
| 25 |
+
"u": 20,
|
| 26 |
+
"v": 21,
|
| 27 |
+
"w": 22,
|
| 28 |
+
"z": 23,
|
| 29 |
+
"æ": 24,
|
| 30 |
+
"ð": 25,
|
| 31 |
+
"ŋ": 26,
|
| 32 |
+
"ɑ": 27,
|
| 33 |
+
"ɔ": 28,
|
| 34 |
+
"ə": 29,
|
| 35 |
+
"ɛ": 30,
|
| 36 |
+
"ɡ": 31,
|
| 37 |
+
"ɪ": 32,
|
| 38 |
+
"ɹ": 33,
|
| 39 |
+
"ɾ": 34,
|
| 40 |
+
"ʃ": 35,
|
| 41 |
+
"ʊ": 36,
|
| 42 |
+
"ʌ": 37,
|
| 43 |
+
"ʒ": 38,
|
| 44 |
+
"ʔ": 39,
|
| 45 |
+
"θ": 40
|
| 46 |
+
},
|
| 47 |
+
"added_tokens_decoder": {
|
| 48 |
+
"0": {
|
| 49 |
+
"content": "<pad>",
|
| 50 |
+
"lstrip": true,
|
| 51 |
+
"normalized": false,
|
| 52 |
+
"rstrip": true,
|
| 53 |
+
"single_word": false,
|
| 54 |
+
"special": false
|
| 55 |
+
},
|
| 56 |
+
"1": {
|
| 57 |
+
"content": "<s>",
|
| 58 |
+
"lstrip": true,
|
| 59 |
+
"normalized": false,
|
| 60 |
+
"rstrip": true,
|
| 61 |
+
"single_word": false,
|
| 62 |
+
"special": false
|
| 63 |
+
},
|
| 64 |
+
"2": {
|
| 65 |
+
"content": "</s>",
|
| 66 |
+
"lstrip": true,
|
| 67 |
+
"normalized": false,
|
| 68 |
+
"rstrip": true,
|
| 69 |
+
"single_word": false,
|
| 70 |
+
"special": false
|
| 71 |
+
},
|
| 72 |
+
"3": {
|
| 73 |
+
"content": "<unk>",
|
| 74 |
+
"lstrip": true,
|
| 75 |
+
"normalized": false,
|
| 76 |
+
"rstrip": true,
|
| 77 |
+
"single_word": false,
|
| 78 |
+
"special": false
|
| 79 |
+
}
|
| 80 |
+
},
|
| 81 |
+
"special_tokens_map": {
|
| 82 |
+
"bos_token": "<s>",
|
| 83 |
+
"eos_token": "</s>",
|
| 84 |
+
"pad_token": "<pad>",
|
| 85 |
+
"unk_token": "<unk>"
|
| 86 |
+
},
|
| 87 |
+
"bos_token": "<s>",
|
| 88 |
+
"eos_token": "</s>",
|
| 89 |
+
"unk_token": "<unk>",
|
| 90 |
+
"pad_token": "<pad>",
|
| 91 |
+
"word_delimiter_token": "|",
|
| 92 |
+
"clean_up_tokenization_spaces": false,
|
| 93 |
+
"do_lower_case": false,
|
| 94 |
+
"model_max_length": 1000000000000000019884624838656
|
| 95 |
+
}
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,49 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "<pad>",
|
| 5 |
+
"lstrip": true,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": true,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": false
|
| 10 |
+
},
|
| 11 |
+
"1": {
|
| 12 |
+
"content": "<s>",
|
| 13 |
+
"lstrip": true,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": true,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": false
|
| 18 |
+
},
|
| 19 |
+
"2": {
|
| 20 |
+
"content": "</s>",
|
| 21 |
+
"lstrip": true,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": true,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": false
|
| 26 |
+
},
|
| 27 |
+
"3": {
|
| 28 |
+
"content": "<unk>",
|
| 29 |
+
"lstrip": true,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": true,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": false
|
| 34 |
+
}
|
| 35 |
+
},
|
| 36 |
+
"bos_token": "<s>",
|
| 37 |
+
"clean_up_tokenization_spaces": false,
|
| 38 |
+
"do_lower_case": false,
|
| 39 |
+
"eos_token": "</s>",
|
| 40 |
+
"extra_special_tokens": {},
|
| 41 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 42 |
+
"pad_token": "<pad>",
|
| 43 |
+
"processor_class": "Wav2Vec2Processor",
|
| 44 |
+
"replace_word_delimiter_char": " ",
|
| 45 |
+
"target_lang": null,
|
| 46 |
+
"tokenizer_class": "Wav2Vec2CTCTokenizer",
|
| 47 |
+
"unk_token": "<unk>",
|
| 48 |
+
"word_delimiter_token": "|"
|
| 49 |
+
}
|
vocab.json
ADDED
|
@@ -0,0 +1,43 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"</s>": 2,
|
| 3 |
+
"<pad>": 0,
|
| 4 |
+
"<s>": 1,
|
| 5 |
+
"<unk>": 3,
|
| 6 |
+
"a": 4,
|
| 7 |
+
"b": 5,
|
| 8 |
+
"d": 6,
|
| 9 |
+
"e": 7,
|
| 10 |
+
"f": 8,
|
| 11 |
+
"h": 9,
|
| 12 |
+
"i": 10,
|
| 13 |
+
"j": 11,
|
| 14 |
+
"k": 12,
|
| 15 |
+
"l": 13,
|
| 16 |
+
"m": 14,
|
| 17 |
+
"n": 15,
|
| 18 |
+
"o": 16,
|
| 19 |
+
"p": 17,
|
| 20 |
+
"s": 18,
|
| 21 |
+
"t": 19,
|
| 22 |
+
"u": 20,
|
| 23 |
+
"v": 21,
|
| 24 |
+
"w": 22,
|
| 25 |
+
"z": 23,
|
| 26 |
+
"æ": 24,
|
| 27 |
+
"ð": 25,
|
| 28 |
+
"ŋ": 26,
|
| 29 |
+
"ɑ": 27,
|
| 30 |
+
"ɔ": 28,
|
| 31 |
+
"ə": 29,
|
| 32 |
+
"ɛ": 30,
|
| 33 |
+
"ɡ": 31,
|
| 34 |
+
"ɪ": 32,
|
| 35 |
+
"ɹ": 33,
|
| 36 |
+
"ɾ": 34,
|
| 37 |
+
"ʃ": 35,
|
| 38 |
+
"ʊ": 36,
|
| 39 |
+
"ʌ": 37,
|
| 40 |
+
"ʒ": 38,
|
| 41 |
+
"ʔ": 39,
|
| 42 |
+
"θ": 40
|
| 43 |
+
}
|