Hugging Face's logo

nacielo
/
wav2GPT2MusiSD3200

Automatic Speech Recognition
Transformers
PyTorch
TensorBoard
speech-encoder-decoder
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
nacielo commited on
Commit
75b42cc
•
1 Parent(s): e993fa1

Training in progress, step 1966

Browse files
Files changed (6) hide show
  1. .gitignore +1 -0
  2. config.json +282 -0
  3. preprocessor_config.json +9 -0
  4. pytorch_model.bin +3 -0
  5. runs/Aug18_15-55-56_node806.pri.csf3.alces.network/events.out.tfevents.1692370579.node806.pri.csf3.alces.network.197226.0 +3 -0
  6. training_args.bin +3 -0
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
config.json ADDED
@@ -0,0 +1,282 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_commit_hash": null,
3
+ "architectures": [
4
+ "SpeechEncoderDecoderModel"
5
+ ],
6
+ "decoder": {
7
+ "_name_or_path": "gpt2",
8
+ "activation_function": "gelu_new",
9
+ "add_cross_attention": true,
10
+ "architectures": [
11
+ "GPT2LMHeadModel"
12
+ ],
13
+ "attn_pdrop": 0.1,
14
+ "bad_words_ids": null,
15
+ "begin_suppress_tokens": null,
16
+ "bos_token_id": 50256,
17
+ "chunk_size_feed_forward": 0,
18
+ "cross_attention_hidden_size": null,
19
+ "decoder_start_token_id": null,
20
+ "diversity_penalty": 0.0,
21
+ "do_sample": false,
22
+ "early_stopping": false,
23
+ "embd_pdrop": 0.1,
24
+ "encoder_no_repeat_ngram_size": 0,
25
+ "eos_token_id": 50256,
26
+ "exponential_decay_length_penalty": null,
27
+ "finetuning_task": null,
28
+ "forced_bos_token_id": null,
29
+ "forced_eos_token_id": null,
30
+ "id2label": {
31
+ "0": "LABEL_0",
32
+ "1": "LABEL_1"
33
+ },
34
+ "initializer_range": 0.02,
35
+ "is_decoder": true,
36
+ "is_encoder_decoder": false,
37
+ "label2id": {
38
+ "LABEL_0": 0,
39
+ "LABEL_1": 1
40
+ },
41
+ "layer_norm_epsilon": 1e-05,
42
+ "length_penalty": 1.0,
43
+ "max_length": 20,
44
+ "min_length": 0,
45
+ "model_type": "gpt2",
46
+ "n_ctx": 1024,
47
+ "n_embd": 768,
48
+ "n_head": 12,
49
+ "n_inner": null,
50
+ "n_layer": 12,
51
+ "n_positions": 1024,
52
+ "no_repeat_ngram_size": 0,
53
+ "num_beam_groups": 1,
54
+ "num_beams": 1,
55
+ "num_return_sequences": 1,
56
+ "output_attentions": false,
57
+ "output_hidden_states": false,
58
+ "output_scores": false,
59
+ "pad_token_id": null,
60
+ "prefix": null,
61
+ "problem_type": null,
62
+ "pruned_heads": {},
63
+ "remove_invalid_values": false,
64
+ "reorder_and_upcast_attn": false,
65
+ "repetition_penalty": 1.0,
66
+ "resid_pdrop": 0.1,
67
+ "return_dict": true,
68
+ "return_dict_in_generate": false,
69
+ "scale_attn_by_inverse_layer_idx": false,
70
+ "scale_attn_weights": true,
71
+ "sep_token_id": null,
72
+ "summary_activation": null,
73
+ "summary_first_dropout": 0.1,
74
+ "summary_proj_to_labels": true,
75
+ "summary_type": "cls_index",
76
+ "summary_use_proj": true,
77
+ "suppress_tokens": null,
78
+ "task_specific_params": {
79
+ "text-generation": {
80
+ "do_sample": true,
81
+ "max_length": 50
82
+ }
83
+ },
84
+ "temperature": 1.0,
85
+ "tf_legacy_loss": false,
86
+ "tie_encoder_decoder": false,
87
+ "tie_word_embeddings": true,
88
+ "tokenizer_class": null,
89
+ "top_k": 50,
90
+ "top_p": 1.0,
91
+ "torch_dtype": null,
92
+ "torchscript": false,
93
+ "transformers_version": "4.31.0",
94
+ "typical_p": 1.0,
95
+ "use_bfloat16": false,
96
+ "use_cache": false,
97
+ "vocab_size": 50257
98
+ },
99
+ "decoder_start_token_id": 50256,
100
+ "encoder": {
101
+ "_name_or_path": "facebook/wav2vec2-base",
102
+ "activation_dropout": 0.0,
103
+ "adapter_attn_dim": null,
104
+ "adapter_kernel_size": 3,
105
+ "adapter_stride": 2,
106
+ "add_adapter": false,
107
+ "add_cross_attention": false,
108
+ "apply_spec_augment": true,
109
+ "architectures": [
110
+ "Wav2Vec2ForPreTraining"
111
+ ],
112
+ "attention_dropout": 0.1,
113
+ "bad_words_ids": null,
114
+ "begin_suppress_tokens": null,
115
+ "bos_token_id": 1,
116
+ "chunk_size_feed_forward": 0,
117
+ "classifier_proj_size": 256,
118
+ "codevector_dim": 256,
119
+ "contrastive_logits_temperature": 0.1,
120
+ "conv_bias": false,
121
+ "conv_dim": [
122
+ 512,
123
+ 512,
124
+ 512,
125
+ 512,
126
+ 512,
127
+ 512,
128
+ 512
129
+ ],
130
+ "conv_kernel": [
131
+ 10,
132
+ 3,
133
+ 3,
134
+ 3,
135
+ 3,
136
+ 2,
137
+ 2
138
+ ],
139
+ "conv_stride": [
140
+ 7,
141
+ 2,
142
+ 2,
143
+ 3,
144
+ 3,
145
+ 3,
146
+ 3
147
+ ],
148
+ "cross_attention_hidden_size": null,
149
+ "ctc_loss_reduction": "sum",
150
+ "ctc_zero_infinity": false,
151
+ "decoder_start_token_id": null,
152
+ "diversity_loss_weight": 0.1,
153
+ "diversity_penalty": 0.0,
154
+ "do_sample": false,
155
+ "do_stable_layer_norm": false,
156
+ "early_stopping": false,
157
+ "encoder_no_repeat_ngram_size": 0,
158
+ "eos_token_id": 2,
159
+ "exponential_decay_length_penalty": null,
160
+ "feat_extract_activation": "gelu",
161
+ "feat_extract_norm": "group",
162
+ "feat_proj_dropout": 0.0,
163
+ "feat_quantizer_dropout": 0.0,
164
+ "final_dropout": 0.0,
165
+ "finetuning_task": null,
166
+ "forced_bos_token_id": null,
167
+ "forced_eos_token_id": null,
168
+ "freeze_feat_extract_train": true,
169
+ "hidden_act": "gelu",
170
+ "hidden_dropout": 0.1,
171
+ "hidden_size": 768,
172
+ "id2label": {
173
+ "0": "LABEL_0",
174
+ "1": "LABEL_1"
175
+ },
176
+ "initializer_range": 0.02,
177
+ "intermediate_size": 3072,
178
+ "is_decoder": false,
179
+ "is_encoder_decoder": false,
180
+ "label2id": {
181
+ "LABEL_0": 0,
182
+ "LABEL_1": 1
183
+ },
184
+ "layer_norm_eps": 1e-05,
185
+ "layerdrop": 0.0,
186
+ "length_penalty": 1.0,
187
+ "mask_channel_length": 10,
188
+ "mask_channel_min_space": 1,
189
+ "mask_channel_other": 0.0,
190
+ "mask_channel_prob": 0.0,
191
+ "mask_channel_selection": "static",
192
+ "mask_feature_length": 10,
193
+ "mask_feature_min_masks": 0,
194
+ "mask_feature_prob": 0.0,
195
+ "mask_time_length": 10,
196
+ "mask_time_min_masks": 2,
197
+ "mask_time_min_space": 1,
198
+ "mask_time_other": 0.0,
199
+ "mask_time_prob": 0.0,
200
+ "mask_time_selection": "static",
201
+ "max_length": 20,
202
+ "min_length": 0,
203
+ "model_type": "wav2vec2",
204
+ "no_mask_channel_overlap": false,
205
+ "no_mask_time_overlap": false,
206
+ "no_repeat_ngram_size": 0,
207
+ "num_adapter_layers": 3,
208
+ "num_attention_heads": 12,
209
+ "num_beam_groups": 1,
210
+ "num_beams": 1,
211
+ "num_codevector_groups": 2,
212
+ "num_codevectors_per_group": 320,
213
+ "num_conv_pos_embedding_groups": 16,
214
+ "num_conv_pos_embeddings": 128,
215
+ "num_feat_extract_layers": 7,
216
+ "num_hidden_layers": 12,
217
+ "num_negatives": 100,
218
+ "num_return_sequences": 1,
219
+ "output_attentions": false,
220
+ "output_hidden_size": 768,
221
+ "output_hidden_states": false,
222
+ "output_scores": false,
223
+ "pad_token_id": 0,
224
+ "prefix": null,
225
+ "problem_type": null,
226
+ "proj_codevector_dim": 256,
227
+ "pruned_heads": {},
228
+ "remove_invalid_values": false,
229
+ "repetition_penalty": 1.0,
230
+ "return_dict": true,
231
+ "return_dict_in_generate": false,
232
+ "sep_token_id": null,
233
+ "suppress_tokens": null,
234
+ "task_specific_params": null,
235
+ "tdnn_dilation": [
236
+ 1,
237
+ 2,
238
+ 3,
239
+ 1,
240
+ 1
241
+ ],
242
+ "tdnn_dim": [
243
+ 512,
244
+ 512,
245
+ 512,
246
+ 512,
247
+ 1500
248
+ ],
249
+ "tdnn_kernel": [
250
+ 5,
251
+ 3,
252
+ 3,
253
+ 1,
254
+ 1
255
+ ],
256
+ "temperature": 1.0,
257
+ "tf_legacy_loss": false,
258
+ "tie_encoder_decoder": false,
259
+ "tie_word_embeddings": true,
260
+ "tokenizer_class": null,
261
+ "top_k": 50,
262
+ "top_p": 1.0,
263
+ "torch_dtype": null,
264
+ "torchscript": false,
265
+ "transformers_version": "4.31.0",
266
+ "typical_p": 1.0,
267
+ "use_bfloat16": false,
268
+ "use_weighted_layer_sum": false,
269
+ "vocab_size": 32,
270
+ "xvector_output_dim": 512
271
+ },
272
+ "eos_token_id": 50256,
273
+ "is_encoder_decoder": true,
274
+ "max_length": 100,
275
+ "model_type": "speech-encoder-decoder",
276
+ "pad_token_id": 50256,
277
+ "processor_class": "Wav2Vec2Processor",
278
+ "tie_word_embeddings": false,
279
+ "torch_dtype": "float32",
280
+ "transformers_version": null,
281
+ "use_cache": false
282
+ }
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:dd0b480a3da1f82a0e0fdc6ce5e5c56d2589fd781167787ea1b29d1f101bb7b2
3
+ size 988869033
runs/Aug18_15-55-56_node806.pri.csf3.alces.network/events.out.tfevents.1692370579.node806.pri.csf3.alces.network.197226.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:833c812433e15554c70c33f24609ad5f9e09c1686cc572e1457abcf6afdf2d09
3
+ size 11563
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2a69d29ceae64551d9204629deead3624a8464af2d9ddf9e7445d47c2080bfe8
3
+ size 4155