Hugging Face's logo

patrickvonplaten
/
wav2vec2-2-bert

Automatic Speech Recognition
Transformers
PyTorch
speech-encoder-decoder
Model card Files
xet
Community
2
Patrick von Platen commited on
Commit
23d055d
·
1 Parent(s): 68fbe39

upload model

Browse files
Files changed (7) hide show
  1. config.json +223 -0
  2. preprocessor_config.json +9 -0
  3. pytorch_model.bin +3 -0
  4. special_tokens_map.json +1 -0
  5. tokenizer.json +0 -0
  6. tokenizer_config.json +1 -0
  7. vocab.txt +0 -0
config.json ADDED
@@ -0,0 +1,223 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "SpeechEncoderDecoderModel"
4
+ ],
5
+ "decoder": {
6
+ "_name_or_path": "bert-large-uncased",
7
+ "add_cross_attention": true,
8
+ "architectures": [
9
+ "BertForMaskedLM"
10
+ ],
11
+ "attention_probs_dropout_prob": 0.1,
12
+ "bad_words_ids": null,
13
+ "bos_token_id": null,
14
+ "chunk_size_feed_forward": 0,
15
+ "classifier_dropout": null,
16
+ "cross_attention_hidden_size": null,
17
+ "decoder_start_token_id": null,
18
+ "diversity_penalty": 0.0,
19
+ "do_sample": false,
20
+ "early_stopping": false,
21
+ "encoder_no_repeat_ngram_size": 0,
22
+ "eos_token_id": null,
23
+ "finetuning_task": null,
24
+ "forced_bos_token_id": null,
25
+ "forced_eos_token_id": null,
26
+ "gradient_checkpointing": false,
27
+ "hidden_act": "gelu",
28
+ "hidden_dropout_prob": 0.1,
29
+ "hidden_size": 1024,
30
+ "id2label": {
31
+ "0": "LABEL_0",
32
+ "1": "LABEL_1"
33
+ },
34
+ "initializer_range": 0.02,
35
+ "intermediate_size": 4096,
36
+ "is_decoder": true,
37
+ "is_encoder_decoder": false,
38
+ "label2id": {
39
+ "LABEL_0": 0,
40
+ "LABEL_1": 1
41
+ },
42
+ "layer_norm_eps": 1e-12,
43
+ "length_penalty": 1.0,
44
+ "max_length": 20,
45
+ "max_position_embeddings": 512,
46
+ "min_length": 0,
47
+ "model_type": "bert",
48
+ "no_repeat_ngram_size": 0,
49
+ "num_attention_heads": 16,
50
+ "num_beam_groups": 1,
51
+ "num_beams": 1,
52
+ "num_hidden_layers": 24,
53
+ "num_return_sequences": 1,
54
+ "output_attentions": false,
55
+ "output_hidden_states": false,
56
+ "output_scores": false,
57
+ "pad_token_id": 0,
58
+ "position_embedding_type": "absolute",
59
+ "prefix": null,
60
+ "problem_type": null,
61
+ "pruned_heads": {},
62
+ "remove_invalid_values": false,
63
+ "repetition_penalty": 1.0,
64
+ "return_dict": true,
65
+ "return_dict_in_generate": false,
66
+ "sep_token_id": null,
67
+ "task_specific_params": null,
68
+ "temperature": 1.0,
69
+ "tie_encoder_decoder": false,
70
+ "tie_word_embeddings": true,
71
+ "tokenizer_class": null,
72
+ "top_k": 50,
73
+ "top_p": 1.0,
74
+ "torch_dtype": null,
75
+ "torchscript": false,
76
+ "transformers_version": "4.14.0.dev0",
77
+ "type_vocab_size": 2,
78
+ "use_bfloat16": false,
79
+ "use_cache": true,
80
+ "vocab_size": 30522
81
+ },
82
+ "encoder": {
83
+ "_name_or_path": "facebook/wav2vec2-large-lv60",
84
+ "activation_dropout": 0.1,
85
+ "adapter_kernel_size": 3,
86
+ "adapter_stride": 2,
87
+ "add_adapter": false,
88
+ "add_cross_attention": false,
89
+ "apply_spec_augment": true,
90
+ "architectures": [
91
+ "Wav2Vec2ForPreTraining"
92
+ ],
93
+ "attention_dropout": 0.1,
94
+ "bad_words_ids": null,
95
+ "bos_token_id": 1,
96
+ "chunk_size_feed_forward": 0,
97
+ "classifier_proj_size": 256,
98
+ "codevector_dim": 768,
99
+ "contrastive_logits_temperature": 0.1,
100
+ "conv_bias": true,
101
+ "conv_dim": [
102
+ 512,
103
+ 512,
104
+ 512,
105
+ 512,
106
+ 512,
107
+ 512,
108
+ 512
109
+ ],
110
+ "conv_kernel": [
111
+ 10,
112
+ 3,
113
+ 3,
114
+ 3,
115
+ 3,
116
+ 2,
117
+ 2
118
+ ],
119
+ "conv_stride": [
120
+ 5,
121
+ 2,
122
+ 2,
123
+ 2,
124
+ 2,
125
+ 2,
126
+ 2
127
+ ],
128
+ "cross_attention_hidden_size": null,
129
+ "ctc_loss_reduction": "sum",
130
+ "ctc_zero_infinity": false,
131
+ "decoder_start_token_id": null,
132
+ "diversity_loss_weight": 0.1,
133
+ "diversity_penalty": 0.0,
134
+ "do_sample": false,
135
+ "do_stable_layer_norm": true,
136
+ "early_stopping": false,
137
+ "encoder_no_repeat_ngram_size": 0,
138
+ "eos_token_id": 2,
139
+ "feat_extract_activation": "gelu",
140
+ "feat_extract_dropout": 0.0,
141
+ "feat_extract_norm": "layer",
142
+ "feat_proj_dropout": 0.1,
143
+ "feat_quantizer_dropout": 0.0,
144
+ "final_dropout": 0.1,
145
+ "finetuning_task": null,
146
+ "forced_bos_token_id": null,
147
+ "forced_eos_token_id": null,
148
+ "gradient_checkpointing": false,
149
+ "hidden_act": "gelu",
150
+ "hidden_dropout": 0.1,
151
+ "hidden_dropout_prob": 0.1,
152
+ "hidden_size": 1024,
153
+ "id2label": {
154
+ "0": "LABEL_0",
155
+ "1": "LABEL_1"
156
+ },
157
+ "initializer_range": 0.02,
158
+ "intermediate_size": 4096,
159
+ "is_decoder": false,
160
+ "is_encoder_decoder": false,
161
+ "label2id": {
162
+ "LABEL_0": 0,
163
+ "LABEL_1": 1
164
+ },
165
+ "layer_norm_eps": 1e-05,
166
+ "layerdrop": 0.1,
167
+ "length_penalty": 1.0,
168
+ "mask_feature_length": 10,
169
+ "mask_feature_min_masks": 0,
170
+ "mask_feature_prob": 0.0,
171
+ "mask_time_length": 10,
172
+ "mask_time_min_masks": 2,
173
+ "mask_time_prob": 0.05,
174
+ "max_length": 20,
175
+ "min_length": 0,
176
+ "model_type": "wav2vec2",
177
+ "no_repeat_ngram_size": 0,
178
+ "num_adapter_layers": 3,
179
+ "num_attention_heads": 16,
180
+ "num_beam_groups": 1,
181
+ "num_beams": 1,
182
+ "num_codevector_groups": 2,
183
+ "num_codevectors_per_group": 320,
184
+ "num_conv_pos_embedding_groups": 16,
185
+ "num_conv_pos_embeddings": 128,
186
+ "num_feat_extract_layers": 7,
187
+ "num_hidden_layers": 24,
188
+ "num_negatives": 100,
189
+ "num_return_sequences": 1,
190
+ "output_attentions": false,
191
+ "output_hidden_size": 1024,
192
+ "output_hidden_states": false,
193
+ "output_scores": false,
194
+ "pad_token_id": 0,
195
+ "prefix": null,
196
+ "problem_type": null,
197
+ "proj_codevector_dim": 768,
198
+ "pruned_heads": {},
199
+ "remove_invalid_values": false,
200
+ "repetition_penalty": 1.0,
201
+ "return_dict": true,
202
+ "return_dict_in_generate": false,
203
+ "sep_token_id": null,
204
+ "task_specific_params": null,
205
+ "temperature": 1.0,
206
+ "tie_encoder_decoder": false,
207
+ "tie_word_embeddings": true,
208
+ "tokenizer_class": null,
209
+ "top_k": 50,
210
+ "top_p": 1.0,
211
+ "torch_dtype": null,
212
+ "torchscript": false,
213
+ "transformers_version": "4.14.0.dev0",
214
+ "use_bfloat16": false,
215
+ "use_weighted_layer_sum": false,
216
+ "vocab_size": 32
217
+ },
218
+ "is_encoder_decoder": true,
219
+ "model_type": "speech-encoder-decoder",
220
+ "tie_word_embeddings": false,
221
+ "torch_dtype": "float32",
222
+ "transformers_version": null
223
+ }
preprocessor_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_normalize": true,
3
+ "feature_extractor_type": "Wav2Vec2FeatureExtractor",
4
+ "feature_size": 1,
5
+ "padding_side": "right",
6
+ "padding_value": 0.0,
7
+ "return_attention_mask": true,
8
+ "sampling_rate": 16000
9
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4c623b867bb4424842a7b6998de5c01bf1a65924c5dc0565a479167bebcc1c3a
3
+ size 3006121656
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"do_lower_case": true, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "bert-large-uncased", "tokenizer_class": "BertTokenizer"}
vocab.txt ADDED
The diff for this file is too large to render. See raw diff