Hugging Face's logo

nacielo
/
wav2BertMusicfreeze

Automatic Speech Recognition
Transformers
PyTorch
TensorBoard
speech-encoder-decoder
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
nacielo commited on
Commit
e77637f
•
1 Parent(s): 8b67f47

Training in progress, step 3403

Browse files
Files changed (6) hide show
  1. .gitignore +1 -0
  2. config.json +302 -0
  3. preprocessor_config.json +9 -0
  4. pytorch_model.bin +3 -0
  5. runs/Aug13_23-21-20_node807.pri.csf3.alces.network/events.out.tfevents.1691965299.node807.pri.csf3.alces.network.47736.0 +3 -0
  6. training_args.bin +3 -0
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
config.json ADDED
@@ -0,0 +1,302 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_commit_hash": null,
3
+ "architectures": [
4
+ "SpeechEncoderDecoderModel"
5
+ ],
6
+ "decoder": {
7
+ "_name_or_path": "facebook/bart-base",
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
+ "BartModel"
15
+ ],
16
+ "attention_dropout": 0.1,
17
+ "bad_words_ids": null,
18
+ "begin_suppress_tokens": null,
19
+ "bos_token_id": 0,
20
+ "chunk_size_feed_forward": 0,
21
+ "classif_dropout": 0.1,
22
+ "classifier_dropout": 0.0,
23
+ "cross_attention_hidden_size": null,
24
+ "d_model": 768,
25
+ "decoder_attention_heads": 12,
26
+ "decoder_ffn_dim": 3072,
27
+ "decoder_layerdrop": 0.0,
28
+ "decoder_layers": 6,
29
+ "decoder_start_token_id": 2,
30
+ "diversity_penalty": 0.0,
31
+ "do_sample": false,
32
+ "dropout": 0.1,
33
+ "early_stopping": true,
34
+ "encoder_attention_heads": 12,
35
+ "encoder_ffn_dim": 3072,
36
+ "encoder_layerdrop": 0.0,
37
+ "encoder_layers": 6,
38
+ "encoder_no_repeat_ngram_size": 0,
39
+ "eos_token_id": 2,
40
+ "exponential_decay_length_penalty": null,
41
+ "finetuning_task": null,
42
+ "forced_bos_token_id": 0,
43
+ "forced_eos_token_id": 2,
44
+ "gradient_checkpointing": false,
45
+ "id2label": {
46
+ "0": "LABEL_0",
47
+ "1": "LABEL_1",
48
+ "2": "LABEL_2"
49
+ },
50
+ "init_std": 0.02,
51
+ "is_decoder": true,
52
+ "is_encoder_decoder": false,
53
+ "label2id": {
54
+ "LABEL_0": 0,
55
+ "LABEL_1": 1,
56
+ "LABEL_2": 2
57
+ },
58
+ "length_penalty": 1.0,
59
+ "max_length": 20,
60
+ "max_position_embeddings": 1024,
61
+ "min_length": 0,
62
+ "model_type": "bart",
63
+ "no_repeat_ngram_size": 3,
64
+ "normalize_before": false,
65
+ "normalize_embedding": true,
66
+ "num_beam_groups": 1,
67
+ "num_beams": 4,
68
+ "num_hidden_layers": 6,
69
+ "num_return_sequences": 1,
70
+ "output_attentions": false,
71
+ "output_hidden_states": false,
72
+ "output_scores": false,
73
+ "pad_token_id": 1,
74
+ "prefix": null,
75
+ "problem_type": null,
76
+ "pruned_heads": {},
77
+ "remove_invalid_values": false,
78
+ "repetition_penalty": 1.0,
79
+ "return_dict": true,
80
+ "return_dict_in_generate": false,
81
+ "scale_embedding": false,
82
+ "sep_token_id": null,
83
+ "suppress_tokens": null,
84
+ "task_specific_params": {
85
+ "summarization": {
86
+ "length_penalty": 1.0,
87
+ "max_length": 128,
88
+ "min_length": 12,
89
+ "num_beams": 4
90
+ },
91
+ "summarization_cnn": {
92
+ "length_penalty": 2.0,
93
+ "max_length": 142,
94
+ "min_length": 56,
95
+ "num_beams": 4
96
+ },
97
+ "summarization_xsum": {
98
+ "length_penalty": 1.0,
99
+ "max_length": 62,
100
+ "min_length": 11,
101
+ "num_beams": 6
102
+ }
103
+ },
104
+ "temperature": 1.0,
105
+ "tf_legacy_loss": false,
106
+ "tie_encoder_decoder": false,
107
+ "tie_word_embeddings": true,
108
+ "tokenizer_class": null,
109
+ "top_k": 50,
110
+ "top_p": 1.0,
111
+ "torch_dtype": "float32",
112
+ "torchscript": false,
113
+ "transformers_version": "4.31.0",
114
+ "typical_p": 1.0,
115
+ "use_bfloat16": false,
116
+ "use_cache": true,
117
+ "vocab_size": 50265
118
+ },
119
+ "decoder_start_token_id": 0,
120
+ "encoder": {
121
+ "_name_or_path": "facebook/wav2vec2-base",
122
+ "activation_dropout": 0.0,
123
+ "adapter_attn_dim": null,
124
+ "adapter_kernel_size": 3,
125
+ "adapter_stride": 2,
126
+ "add_adapter": false,
127
+ "add_cross_attention": false,
128
+ "apply_spec_augment": true,
129
+ "architectures": [
130
+ "Wav2Vec2ForPreTraining"
131
+ ],
132
+ "attention_dropout": 0.1,
133
+ "bad_words_ids": null,
134
+ "begin_suppress_tokens": null,
135
+ "bos_token_id": 1,
136
+ "chunk_size_feed_forward": 0,
137
+ "classifier_proj_size": 256,
138
+ "codevector_dim": 256,
139
+ "contrastive_logits_temperature": 0.1,
140
+ "conv_bias": false,
141
+ "conv_dim": [
142
+ 512,
143
+ 512,
144
+ 512,
145
+ 512,
146
+ 512,
147
+ 512,
148
+ 512
149
+ ],
150
+ "conv_kernel": [
151
+ 10,
152
+ 3,
153
+ 3,
154
+ 3,
155
+ 3,
156
+ 2,
157
+ 2
158
+ ],
159
+ "conv_stride": [
160
+ 5,
161
+ 2,
162
+ 2,
163
+ 2,
164
+ 2,
165
+ 2,
166
+ 2
167
+ ],
168
+ "cross_attention_hidden_size": null,
169
+ "ctc_loss_reduction": "sum",
170
+ "ctc_zero_infinity": false,
171
+ "decoder_start_token_id": null,
172
+ "diversity_loss_weight": 0.1,
173
+ "diversity_penalty": 0.0,
174
+ "do_sample": false,
175
+ "do_stable_layer_norm": false,
176
+ "early_stopping": false,
177
+ "encoder_no_repeat_ngram_size": 0,
178
+ "eos_token_id": 2,
179
+ "exponential_decay_length_penalty": null,
180
+ "feat_extract_activation": "gelu",
181
+ "feat_extract_norm": "group",
182
+ "feat_proj_dropout": 0.0,
183
+ "feat_quantizer_dropout": 0.0,
184
+ "final_dropout": 0.0,
185
+ "finetuning_task": null,
186
+ "forced_bos_token_id": null,
187
+ "forced_eos_token_id": null,
188
+ "freeze_feat_extract_train": true,
189
+ "hidden_act": "gelu",
190
+ "hidden_dropout": 0.1,
191
+ "hidden_size": 768,
192
+ "id2label": {
193
+ "0": "LABEL_0",
194
+ "1": "LABEL_1"
195
+ },
196
+ "initializer_range": 0.02,
197
+ "intermediate_size": 3072,
198
+ "is_decoder": false,
199
+ "is_encoder_decoder": false,
200
+ "label2id": {
201
+ "LABEL_0": 0,
202
+ "LABEL_1": 1
203
+ },
204
+ "layer_norm_eps": 1e-05,
205
+ "layerdrop": 0.0,
206
+ "length_penalty": 1.0,
207
+ "mask_channel_length": 10,
208
+ "mask_channel_min_space": 1,
209
+ "mask_channel_other": 0.0,
210
+ "mask_channel_prob": 0.0,
211
+ "mask_channel_selection": "static",
212
+ "mask_feature_length": 10,
213
+ "mask_feature_min_masks": 0,
214
+ "mask_feature_prob": 0.0,
215
+ "mask_time_length": 10,
216
+ "mask_time_min_masks": 2,
217
+ "mask_time_min_space": 1,
218
+ "mask_time_other": 0.0,
219
+ "mask_time_prob": 0.0,
220
+ "mask_time_selection": "static",
221
+ "max_length": 20,
222
+ "min_length": 0,
223
+ "model_type": "wav2vec2",
224
+ "no_mask_channel_overlap": false,
225
+ "no_mask_time_overlap": false,
226
+ "no_repeat_ngram_size": 0,
227
+ "num_adapter_layers": 3,
228
+ "num_attention_heads": 12,
229
+ "num_beam_groups": 1,
230
+ "num_beams": 1,
231
+ "num_codevector_groups": 2,
232
+ "num_codevectors_per_group": 320,
233
+ "num_conv_pos_embedding_groups": 16,
234
+ "num_conv_pos_embeddings": 128,
235
+ "num_feat_extract_layers": 7,
236
+ "num_hidden_layers": 12,
237
+ "num_negatives": 100,
238
+ "num_return_sequences": 1,
239
+ "output_attentions": false,
240
+ "output_hidden_size": 768,
241
+ "output_hidden_states": false,
242
+ "output_scores": false,
243
+ "pad_token_id": 0,
244
+ "prefix": null,
245
+ "problem_type": null,
246
+ "proj_codevector_dim": 256,
247
+ "pruned_heads": {},
248
+ "remove_invalid_values": false,
249
+ "repetition_penalty": 1.0,
250
+ "return_dict": true,
251
+ "return_dict_in_generate": false,
252
+ "sep_token_id": null,
253
+ "suppress_tokens": null,
254
+ "task_specific_params": null,
255
+ "tdnn_dilation": [
256
+ 1,
257
+ 2,
258
+ 3,
259
+ 1,
260
+ 1
261
+ ],
262
+ "tdnn_dim": [
263
+ 512,
264
+ 512,
265
+ 512,
266
+ 512,
267
+ 1500
268
+ ],
269
+ "tdnn_kernel": [
270
+ 5,
271
+ 3,
272
+ 3,
273
+ 1,
274
+ 1
275
+ ],
276
+ "temperature": 1.0,
277
+ "tf_legacy_loss": false,
278
+ "tie_encoder_decoder": false,
279
+ "tie_word_embeddings": true,
280
+ "tokenizer_class": null,
281
+ "top_k": 50,
282
+ "top_p": 1.0,
283
+ "torch_dtype": null,
284
+ "torchscript": false,
285
+ "transformers_version": "4.31.0",
286
+ "typical_p": 1.0,
287
+ "use_bfloat16": false,
288
+ "use_weighted_layer_sum": false,
289
+ "vocab_size": 32,
290
+ "xvector_output_dim": 512
291
+ },
292
+ "eos_token_id": 2,
293
+ "is_encoder_decoder": true,
294
+ "max_length": 100,
295
+ "model_type": "speech-encoder-decoder",
296
+ "pad_token_id": 1,
297
+ "processor_class": "Wav2Vec2Processor",
298
+ "tie_word_embeddings": false,
299
+ "torch_dtype": "float32",
300
+ "transformers_version": null,
301
+ "use_cache": false
302
+ }
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": false,
8
+ "sampling_rate": 16000
9
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:782a581f2393ee02668763b63f12405a5efd62a6d131b39b524af64d15d9a1d0
3
+ size 762030361
runs/Aug13_23-21-20_node807.pri.csf3.alces.network/events.out.tfevents.1691965299.node807.pri.csf3.alces.network.47736.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8a8603ef2e51d8e64ce1dea5e423b10c8ebaf3599d3107973e766ea6752ae24c
3
+ size 13062
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8a08c36f481e1dd234a7a26d49b0ff1f0486ae0c94243b11916560cf731dba85
3
+ size 4155