Hugging Face's logo

wbbbbb
/
chinese-speech-rec

Automatic Speech Recognition
Transformers
PyTorch
speech-encoder-decoder
Inference Endpoints
Model card Files Community
2
wbbbbb commited on
Commit
d70e28c
•
1 Parent(s): f1d28f1

Upload config.json

Browse files
Files changed (1) hide show
  1. config.json +274 -0
config.json ADDED
@@ -0,0 +1,274 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "wav2vec2-bart-pre",
3
+ "architectures": [
4
+ "SpeechEncoderDecoderModel"
5
+ ],
6
+ "decoder": {
7
+ "_name_or_path": "IDEA-CCNL/Randeng-BART-139M",
8
+ "activation_dropout": 0.1,
9
+ "activation_function": "gelu",
10
+ "add_bias_logits": false,
11
+ "add_cross_attention": true,
12
+ "add_final_layer_norm": false,
13
+ "architectures": [
14
+ "BartForConditionalGeneration"
15
+ ],
16
+ "attention_dropout": 0.1,
17
+ "bad_words_ids": null,
18
+ "bos_token_id": 0,
19
+ "chunk_size_feed_forward": 0,
20
+ "classif_dropout": 0.1,
21
+ "classifier_dropout": 0.0,
22
+ "cross_attention_hidden_size": null,
23
+ "d_model": 768,
24
+ "decoder_attention_heads": 12,
25
+ "decoder_ffn_dim": 3072,
26
+ "decoder_layerdrop": 0.0,
27
+ "decoder_layers": 6,
28
+ "decoder_start_token_id": 2,
29
+ "diversity_penalty": 0.0,
30
+ "do_sample": false,
31
+ "dropout": 0.1,
32
+ "early_stopping": false,
33
+ "encoder_attention_heads": 12,
34
+ "encoder_ffn_dim": 3072,
35
+ "encoder_layerdrop": 0.0,
36
+ "encoder_layers": 6,
37
+ "encoder_no_repeat_ngram_size": 0,
38
+ "eos_token_id": 2,
39
+ "exponential_decay_length_penalty": null,
40
+ "finetuning_task": null,
41
+ "forced_bos_token_id": null,
42
+ "forced_eos_token_id": 2,
43
+ "id2label": {
44
+ "0": "LABEL_0",
45
+ "1": "LABEL_1",
46
+ "2": "LABEL_2"
47
+ },
48
+ "init_std": 0.02,
49
+ "is_decoder": true,
50
+ "is_encoder_decoder": false,
51
+ "label2id": {
52
+ "LABEL_0": 0,
53
+ "LABEL_1": 1,
54
+ "LABEL_2": 2
55
+ },
56
+ "length_penalty": 1.0,
57
+ "max_length": 20,
58
+ "max_position_embeddings": 1024,
59
+ "min_length": 0,
60
+ "model_type": "bart",
61
+ "no_repeat_ngram_size": 3,
62
+ "normalize_before": false,
63
+ "normalize_embedding": true,
64
+ "num_beam_groups": 1,
65
+ "num_beams": 4,
66
+ "num_hidden_layers": 6,
67
+ "num_return_sequences": 1,
68
+ "output_attentions": false,
69
+ "output_hidden_states": false,
70
+ "output_scores": false,
71
+ "pad_token_id": 1,
72
+ "prefix": null,
73
+ "problem_type": null,
74
+ "pruned_heads": {},
75
+ "remove_invalid_values": false,
76
+ "repetition_penalty": 1.0,
77
+ "return_dict": true,
78
+ "return_dict_in_generate": false,
79
+ "scale_embedding": false,
80
+ "sep_token_id": null,
81
+ "task_specific_params": null,
82
+ "temperature": 1.0,
83
+ "tf_legacy_loss": false,
84
+ "tie_encoder_decoder": false,
85
+ "tie_word_embeddings": true,
86
+ "tokenizer_class": null,
87
+ "top_k": 50,
88
+ "top_p": 1.0,
89
+ "torch_dtype": "float16",
90
+ "torchscript": false,
91
+ "transformers_version": "4.21.0",
92
+ "typical_p": 1.0,
93
+ "use_bfloat16": false,
94
+ "use_cache": false,
95
+ "vocab_size": 50265
96
+ },
97
+ "decoder_start_token_id": 0,
98
+ "encoder": {
99
+ "_name_or_path": "wbbbbb/wav2vec2-large-chinese-zh-cn",
100
+ "activation_dropout": 0.0,
101
+ "adapter_kernel_size": 3,
102
+ "adapter_stride": 2,
103
+ "add_adapter": true,
104
+ "add_cross_attention": false,
105
+ "apply_spec_augment": true,
106
+ "architectures": [
107
+ "Wav2Vec2ForPreTraining"
108
+ ],
109
+ "attention_dropout": 0.0,
110
+ "bad_words_ids": null,
111
+ "bos_token_id": 1,
112
+ "chunk_size_feed_forward": 0,
113
+ "classifier_proj_size": 256,
114
+ "codevector_dim": 768,
115
+ "contrastive_logits_temperature": 0.1,
116
+ "conv_bias": true,
117
+ "conv_dim": [
118
+ 512,
119
+ 512,
120
+ 512,
121
+ 512,
122
+ 512,
123
+ 512,
124
+ 512
125
+ ],
126
+ "conv_kernel": [
127
+ 10,
128
+ 3,
129
+ 3,
130
+ 3,
131
+ 3,
132
+ 2,
133
+ 2
134
+ ],
135
+ "conv_stride": [
136
+ 5,
137
+ 2,
138
+ 2,
139
+ 2,
140
+ 2,
141
+ 2,
142
+ 2
143
+ ],
144
+ "cross_attention_hidden_size": null,
145
+ "ctc_loss_reduction": "mean",
146
+ "ctc_zero_infinity": false,
147
+ "decoder_start_token_id": null,
148
+ "diversity_loss_weight": 0.1,
149
+ "diversity_penalty": 0.0,
150
+ "do_sample": false,
151
+ "do_stable_layer_norm": true,
152
+ "early_stopping": false,
153
+ "encoder_no_repeat_ngram_size": 0,
154
+ "eos_token_id": 2,
155
+ "exponential_decay_length_penalty": null,
156
+ "feat_extract_activation": "gelu",
157
+ "feat_extract_dropout": 0.0,
158
+ "feat_extract_norm": "layer",
159
+ "feat_proj_dropout": 0.0,
160
+ "feat_quantizer_dropout": 0.0,
161
+ "final_dropout": 0.0,
162
+ "finetuning_task": null,
163
+ "forced_bos_token_id": null,
164
+ "forced_eos_token_id": null,
165
+ "hidden_act": "gelu",
166
+ "hidden_dropout": 0.0,
167
+ "hidden_size": 1024,
168
+ "id2label": {
169
+ "0": "LABEL_0",
170
+ "1": "LABEL_1"
171
+ },
172
+ "initializer_range": 0.02,
173
+ "intermediate_size": 4096,
174
+ "is_decoder": false,
175
+ "is_encoder_decoder": false,
176
+ "label2id": {
177
+ "LABEL_0": 0,
178
+ "LABEL_1": 1
179
+ },
180
+ "layer_norm_eps": 1e-05,
181
+ "layerdrop": 0.0,
182
+ "length_penalty": 1.0,
183
+ "mask_channel_length": 10,
184
+ "mask_channel_min_space": 1,
185
+ "mask_channel_other": 0.0,
186
+ "mask_channel_prob": 0.0,
187
+ "mask_channel_selection": "static",
188
+ "mask_feature_length": 10,
189
+ "mask_feature_min_masks": 0,
190
+ "mask_feature_prob": 0.0,
191
+ "mask_time_length": 10,
192
+ "mask_time_min_masks": 2,
193
+ "mask_time_min_space": 1,
194
+ "mask_time_other": 0.0,
195
+ "mask_time_prob": 0.05,
196
+ "mask_time_selection": "static",
197
+ "max_length": 20,
198
+ "min_length": 0,
199
+ "model_type": "wav2vec2",
200
+ "no_repeat_ngram_size": 0,
201
+ "num_adapter_layers": 3,
202
+ "num_attention_heads": 16,
203
+ "num_beam_groups": 1,
204
+ "num_beams": 1,
205
+ "num_codevector_groups": 2,
206
+ "num_codevectors_per_group": 320,
207
+ "num_conv_pos_embedding_groups": 16,
208
+ "num_conv_pos_embeddings": 128,
209
+ "num_feat_extract_layers": 7,
210
+ "num_hidden_layers": 24,
211
+ "num_negatives": 100,
212
+ "num_return_sequences": 1,
213
+ "output_attentions": false,
214
+ "output_hidden_size": 1024,
215
+ "output_hidden_states": false,
216
+ "output_scores": false,
217
+ "pad_token_id": 5168,
218
+ "prefix": null,
219
+ "problem_type": null,
220
+ "proj_codevector_dim": 768,
221
+ "pruned_heads": {},
222
+ "remove_invalid_values": false,
223
+ "repetition_penalty": 1.0,
224
+ "return_dict": true,
225
+ "return_dict_in_generate": false,
226
+ "sep_token_id": null,
227
+ "task_specific_params": null,
228
+ "tdnn_dilation": [
229
+ 1,
230
+ 2,
231
+ 3,
232
+ 1,
233
+ 1
234
+ ],
235
+ "tdnn_dim": [
236
+ 512,
237
+ 512,
238
+ 512,
239
+ 512,
240
+ 1500
241
+ ],
242
+ "tdnn_kernel": [
243
+ 5,
244
+ 3,
245
+ 3,
246
+ 1,
247
+ 1
248
+ ],
249
+ "temperature": 1.0,
250
+ "tf_legacy_loss": false,
251
+ "tie_encoder_decoder": false,
252
+ "tie_word_embeddings": true,
253
+ "tokenizer_class": null,
254
+ "top_k": 50,
255
+ "top_p": 1.0,
256
+ "torch_dtype": "float32",
257
+ "torchscript": false,
258
+ "transformers_version": "4.21.0",
259
+ "typical_p": 1.0,
260
+ "use_bfloat16": false,
261
+ "use_weighted_layer_sum": false,
262
+ "vocab_size": 5171,
263
+ "xvector_output_dim": 512
264
+ },
265
+ "eos_token_id": 2,
266
+ "is_encoder_decoder": true,
267
+ "max_length": 200,
268
+ "model_type": "speech-encoder-decoder",
269
+ "num_beams": 5,
270
+ "pad_token_id": 1,
271
+ "tie_word_embeddings": false,
272
+ "torch_dtype": "float32",
273
+ "transformers_version": null
274
+ }