Hugging Face's logo

nacielo
/
privateuse

Automatic Speech Recognition
Transformers
PyTorch
TensorBoard
speech-encoder-decoder
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
nacielo commited on
Commit
1fd384c
•
1 Parent(s): 6d2a7f9

Model save

Browse files
Files changed (11) hide show
  1. .gitignore +1 -0
  2. config.json +272 -0
  3. generation_config.json +7 -0
  4. merges.txt +0 -0
  5. pytorch_model.bin +3 -0
  6. runs/Aug01_17-09-58_ac2707491e04/events.out.tfevents.1690909808.ac2707491e04.287.0 +3 -0
  7. special_tokens_map.json +6 -0
  8. tokenizer.json +0 -0
  9. tokenizer_config.json +9 -0
  10. training_args.bin +3 -0
  11. vocab.json +0 -0
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
config.json ADDED
@@ -0,0 +1,272 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_commit_hash": "c32ae78749c90f4225b9f1d23ecf3a539faa839c",
3
+ "_name_or_path": "nacielo/wav2vec2-gpt",
4
+ "architectures": [
5
+ "SpeechEncoderDecoderModel"
6
+ ],
7
+ "decoder": {
8
+ "_name_or_path": "gpt2",
9
+ "activation_function": "gelu_new",
10
+ "add_cross_attention": true,
11
+ "architectures": [
12
+ "GPT2LMHeadModel"
13
+ ],
14
+ "attn_pdrop": 0.1,
15
+ "bad_words_ids": null,
16
+ "begin_suppress_tokens": null,
17
+ "bos_token_id": 50256,
18
+ "chunk_size_feed_forward": 0,
19
+ "cross_attention_hidden_size": null,
20
+ "decoder_start_token_id": null,
21
+ "diversity_penalty": 0.0,
22
+ "do_sample": false,
23
+ "early_stopping": false,
24
+ "embd_pdrop": 0.1,
25
+ "encoder_no_repeat_ngram_size": 0,
26
+ "eos_token_id": 50256,
27
+ "exponential_decay_length_penalty": null,
28
+ "finetuning_task": null,
29
+ "forced_bos_token_id": null,
30
+ "forced_eos_token_id": null,
31
+ "id2label": {
32
+ "0": "LABEL_0",
33
+ "1": "LABEL_1"
34
+ },
35
+ "initializer_range": 0.02,
36
+ "is_decoder": true,
37
+ "is_encoder_decoder": false,
38
+ "label2id": {
39
+ "LABEL_0": 0,
40
+ "LABEL_1": 1
41
+ },
42
+ "layer_norm_epsilon": 1e-05,
43
+ "length_penalty": 1.0,
44
+ "max_length": 20,
45
+ "min_length": 0,
46
+ "model_type": "gpt2",
47
+ "n_ctx": 1024,
48
+ "n_embd": 768,
49
+ "n_head": 12,
50
+ "n_inner": null,
51
+ "n_layer": 12,
52
+ "n_positions": 1024,
53
+ "no_repeat_ngram_size": 0,
54
+ "num_beam_groups": 1,
55
+ "num_beams": 1,
56
+ "num_return_sequences": 1,
57
+ "output_attentions": false,
58
+ "output_hidden_states": false,
59
+ "output_scores": false,
60
+ "pad_token_id": null,
61
+ "prefix": null,
62
+ "problem_type": null,
63
+ "pruned_heads": {},
64
+ "remove_invalid_values": false,
65
+ "reorder_and_upcast_attn": false,
66
+ "repetition_penalty": 1.0,
67
+ "resid_pdrop": 0.1,
68
+ "return_dict": true,
69
+ "return_dict_in_generate": false,
70
+ "scale_attn_by_inverse_layer_idx": false,
71
+ "scale_attn_weights": true,
72
+ "sep_token_id": null,
73
+ "summary_activation": null,
74
+ "summary_first_dropout": 0.1,
75
+ "summary_proj_to_labels": true,
76
+ "summary_type": "cls_index",
77
+ "summary_use_proj": true,
78
+ "suppress_tokens": null,
79
+ "task_specific_params": {
80
+ "text-generation": {
81
+ "do_sample": true,
82
+ "max_length": 50
83
+ }
84
+ },
85
+ "temperature": 1.0,
86
+ "tf_legacy_loss": false,
87
+ "tie_encoder_decoder": false,
88
+ "tie_word_embeddings": true,
89
+ "tokenizer_class": null,
90
+ "top_k": 50,
91
+ "top_p": 1.0,
92
+ "torch_dtype": null,
93
+ "torchscript": false,
94
+ "transformers_version": "4.31.0",
95
+ "typical_p": 1.0,
96
+ "use_bfloat16": false,
97
+ "use_cache": true,
98
+ "vocab_size": 50257
99
+ },
100
+ "decoder_start_token_id": 50256,
101
+ "encoder": {
102
+ "_name_or_path": "facebook/wav2vec2-base-960h",
103
+ "activation_dropout": 0.1,
104
+ "adapter_attn_dim": null,
105
+ "adapter_kernel_size": 3,
106
+ "adapter_stride": 2,
107
+ "add_adapter": false,
108
+ "add_cross_attention": false,
109
+ "apply_spec_augment": true,
110
+ "architectures": [
111
+ "Wav2Vec2ForCTC"
112
+ ],
113
+ "attention_dropout": 0.1,
114
+ "bad_words_ids": null,
115
+ "begin_suppress_tokens": null,
116
+ "bos_token_id": 1,
117
+ "chunk_size_feed_forward": 0,
118
+ "classifier_proj_size": 256,
119
+ "codevector_dim": 256,
120
+ "contrastive_logits_temperature": 0.1,
121
+ "conv_bias": false,
122
+ "conv_dim": [
123
+ 512,
124
+ 512,
125
+ 512,
126
+ 512,
127
+ 512,
128
+ 512,
129
+ 512
130
+ ],
131
+ "conv_kernel": [
132
+ 10,
133
+ 3,
134
+ 3,
135
+ 3,
136
+ 3,
137
+ 2,
138
+ 2
139
+ ],
140
+ "conv_stride": [
141
+ 5,
142
+ 2,
143
+ 2,
144
+ 2,
145
+ 2,
146
+ 2,
147
+ 2
148
+ ],
149
+ "cross_attention_hidden_size": null,
150
+ "ctc_loss_reduction": "sum",
151
+ "ctc_zero_infinity": false,
152
+ "decoder_start_token_id": null,
153
+ "diversity_loss_weight": 0.1,
154
+ "diversity_penalty": 0.0,
155
+ "do_sample": false,
156
+ "do_stable_layer_norm": false,
157
+ "early_stopping": false,
158
+ "encoder_no_repeat_ngram_size": 0,
159
+ "eos_token_id": 2,
160
+ "exponential_decay_length_penalty": null,
161
+ "feat_extract_activation": "gelu",
162
+ "feat_extract_dropout": 0.0,
163
+ "feat_extract_norm": "group",
164
+ "feat_proj_dropout": 0.1,
165
+ "feat_quantizer_dropout": 0.0,
166
+ "final_dropout": 0.1,
167
+ "finetuning_task": null,
168
+ "forced_bos_token_id": null,
169
+ "forced_eos_token_id": null,
170
+ "gradient_checkpointing": false,
171
+ "hidden_act": "gelu",
172
+ "hidden_dropout": 0.1,
173
+ "hidden_dropout_prob": 0.1,
174
+ "hidden_size": 768,
175
+ "id2label": {
176
+ "0": "LABEL_0",
177
+ "1": "LABEL_1"
178
+ },
179
+ "initializer_range": 0.02,
180
+ "intermediate_size": 3072,
181
+ "is_decoder": false,
182
+ "is_encoder_decoder": false,
183
+ "label2id": {
184
+ "LABEL_0": 0,
185
+ "LABEL_1": 1
186
+ },
187
+ "layer_norm_eps": 1e-05,
188
+ "layerdrop": 0.1,
189
+ "length_penalty": 1.0,
190
+ "mask_feature_length": 10,
191
+ "mask_feature_min_masks": 0,
192
+ "mask_feature_prob": 0.0,
193
+ "mask_time_length": 10,
194
+ "mask_time_min_masks": 2,
195
+ "mask_time_prob": 0.05,
196
+ "max_length": 20,
197
+ "min_length": 0,
198
+ "model_type": "wav2vec2",
199
+ "no_repeat_ngram_size": 0,
200
+ "num_adapter_layers": 3,
201
+ "num_attention_heads": 12,
202
+ "num_beam_groups": 1,
203
+ "num_beams": 1,
204
+ "num_codevector_groups": 2,
205
+ "num_codevectors_per_group": 320,
206
+ "num_conv_pos_embedding_groups": 16,
207
+ "num_conv_pos_embeddings": 128,
208
+ "num_feat_extract_layers": 7,
209
+ "num_hidden_layers": 12,
210
+ "num_negatives": 100,
211
+ "num_return_sequences": 1,
212
+ "output_attentions": false,
213
+ "output_hidden_size": 768,
214
+ "output_hidden_states": false,
215
+ "output_scores": false,
216
+ "pad_token_id": 0,
217
+ "prefix": null,
218
+ "problem_type": null,
219
+ "proj_codevector_dim": 256,
220
+ "pruned_heads": {},
221
+ "remove_invalid_values": false,
222
+ "repetition_penalty": 1.0,
223
+ "return_dict": true,
224
+ "return_dict_in_generate": false,
225
+ "sep_token_id": null,
226
+ "suppress_tokens": 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": null,
257
+ "torchscript": false,
258
+ "transformers_version": "4.31.0",
259
+ "typical_p": 1.0,
260
+ "use_bfloat16": false,
261
+ "use_weighted_layer_sum": false,
262
+ "vocab_size": 32,
263
+ "xvector_output_dim": 512
264
+ },
265
+ "eos_token_id": 50256,
266
+ "is_encoder_decoder": true,
267
+ "model_type": "speech-encoder-decoder",
268
+ "pad_token_id": 50256,
269
+ "tie_word_embeddings": false,
270
+ "torch_dtype": "float32",
271
+ "transformers_version": null
272
+ }
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 50256,
3
+ "decoder_start_token_id": 50256,
4
+ "eos_token_id": 50256,
5
+ "pad_token_id": 50256,
6
+ "transformers_version": "4.31.0"
7
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:085811dd644eb4c437aa9f2b2e440f5db0c46b622ac859b29e1877cbb8737a2c
3
+ size 988869033
runs/Aug01_17-09-58_ac2707491e04/events.out.tfevents.1690909808.ac2707491e04.287.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a603e9442e4a2bc8a2ff27afcdb6a0c00010691433a2352c3b9b42c4b8853d79
3
+ size 11118
special_tokens_map.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<|endoftext|>",
3
+ "eos_token": "<|endoftext|>",
4
+ "pad_token": "<|endoftext|>",
5
+ "unk_token": "<|endoftext|>"
6
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "bos_token": "<|endoftext|>",
4
+ "clean_up_tokenization_spaces": true,
5
+ "eos_token": "<|endoftext|>",
6
+ "model_max_length": 1024,
7
+ "tokenizer_class": "GPT2Tokenizer",
8
+ "unk_token": "<|endoftext|>"
9
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:20f2a872edcb0b24b075e48d3d558f108dfc9aa23e956430cecc8798a5afeb4a
3
+ size 4091
vocab.json ADDED
The diff for this file is too large to render. See raw diff