Hugging Face's logo

TheRamsay
/
wav2vec2-gpt2-enc-dec-reduced

Automatic Speech Recognition
Transformers
Safetensors
speech-encoder-decoder
Generated from Trainer
Inference Endpoints
Model card Files Community
TheRamsay commited on
Commit
c9dd641
·
verified ·
1 Parent(s): e9ca164

Training in progress, epoch 1

Browse files
Files changed (8) hide show
  1. config.json +266 -0
  2. merges.txt +0 -0
  3. model.safetensors +3 -0
  4. special_tokens_map.json +24 -0
  5. tokenizer.json +0 -0
  6. tokenizer_config.json +22 -0
  7. training_args.bin +3 -0
  8. vocab.json +0 -0
config.json ADDED
@@ -0,0 +1,266 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "SpeechEncoderDecoderModel"
4
+ ],
5
+ "decoder": {
6
+ "_name_or_path": "fav-kky/gpt2-small-cs",
7
+ "activation_function": "gelu",
8
+ "add_cross_attention": true,
9
+ "architectures": [
10
+ "GPT2LMHeadModel"
11
+ ],
12
+ "attn_pdrop": 0.1,
13
+ "bad_words_ids": null,
14
+ "begin_suppress_tokens": null,
15
+ "bos_token_id": 0,
16
+ "chunk_size_feed_forward": 0,
17
+ "cross_attention_hidden_size": null,
18
+ "decoder_start_token_id": null,
19
+ "diversity_penalty": 0.0,
20
+ "do_sample": false,
21
+ "early_stopping": false,
22
+ "embd_pdrop": 0.1,
23
+ "encoder_no_repeat_ngram_size": 0,
24
+ "eos_token_id": 0,
25
+ "exponential_decay_length_penalty": null,
26
+ "finetuning_task": null,
27
+ "forced_bos_token_id": null,
28
+ "forced_eos_token_id": null,
29
+ "gradient_checkpointing": false,
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": 512,
48
+ "n_head": 8,
49
+ "n_inner": null,
50
+ "n_layer": 2,
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": 1024
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": "float32",
92
+ "torchscript": false,
93
+ "typical_p": 1.0,
94
+ "use_bfloat16": false,
95
+ "use_cache": true,
96
+ "vocab_size": 50000
97
+ },
98
+ "decoder_start_token_id": 0,
99
+ "encoder": {
100
+ "_name_or_path": "fav-kky/wav2vec2-base-cs-80k-ClTRUS",
101
+ "activation_dropout": 0.1,
102
+ "adapter_attn_dim": null,
103
+ "adapter_kernel_size": 3,
104
+ "adapter_stride": 2,
105
+ "add_adapter": false,
106
+ "add_cross_attention": false,
107
+ "apply_spec_augment": true,
108
+ "architectures": [
109
+ "Wav2Vec2ForPreTraining"
110
+ ],
111
+ "attention_dropout": 0.1,
112
+ "bad_words_ids": null,
113
+ "begin_suppress_tokens": null,
114
+ "bos_token_id": 1,
115
+ "chunk_size_feed_forward": 0,
116
+ "classifier_proj_size": 256,
117
+ "codevector_dim": 256,
118
+ "contrastive_logits_temperature": 0.1,
119
+ "conv_bias": false,
120
+ "conv_dim": [
121
+ 512,
122
+ 512,
123
+ 512,
124
+ 512,
125
+ 512,
126
+ 512,
127
+ 512
128
+ ],
129
+ "conv_kernel": [
130
+ 10,
131
+ 3,
132
+ 3,
133
+ 3,
134
+ 3,
135
+ 2,
136
+ 2
137
+ ],
138
+ "conv_stride": [
139
+ 5,
140
+ 2,
141
+ 2,
142
+ 2,
143
+ 2,
144
+ 2,
145
+ 2
146
+ ],
147
+ "cross_attention_hidden_size": null,
148
+ "ctc_loss_reduction": "sum",
149
+ "ctc_zero_infinity": false,
150
+ "decoder_start_token_id": null,
151
+ "diversity_loss_weight": 0.1,
152
+ "diversity_penalty": 0.0,
153
+ "do_sample": false,
154
+ "do_stable_layer_norm": false,
155
+ "early_stopping": false,
156
+ "encoder_no_repeat_ngram_size": 0,
157
+ "eos_token_id": 2,
158
+ "exponential_decay_length_penalty": null,
159
+ "feat_extract_activation": "gelu",
160
+ "feat_extract_norm": "group",
161
+ "feat_proj_dropout": 0.0,
162
+ "feat_quantizer_dropout": 0.0,
163
+ "final_dropout": 0.1,
164
+ "finetuning_task": null,
165
+ "forced_bos_token_id": null,
166
+ "forced_eos_token_id": null,
167
+ "hidden_act": "gelu",
168
+ "hidden_dropout": 0.1,
169
+ "hidden_size": 384,
170
+ "id2label": {
171
+ "0": "LABEL_0",
172
+ "1": "LABEL_1"
173
+ },
174
+ "initializer_range": 0.02,
175
+ "intermediate_size": 1536,
176
+ "is_decoder": false,
177
+ "is_encoder_decoder": false,
178
+ "label2id": {
179
+ "LABEL_0": 0,
180
+ "LABEL_1": 1
181
+ },
182
+ "layer_norm_eps": 1e-05,
183
+ "layerdrop": 0.1,
184
+ "length_penalty": 1.0,
185
+ "mask_feature_length": 10,
186
+ "mask_feature_min_masks": 0,
187
+ "mask_feature_prob": 0.0,
188
+ "mask_time_length": 10,
189
+ "mask_time_min_masks": 2,
190
+ "mask_time_prob": 0.05,
191
+ "max_length": 20,
192
+ "min_length": 0,
193
+ "model_type": "wav2vec2",
194
+ "no_repeat_ngram_size": 0,
195
+ "num_adapter_layers": 3,
196
+ "num_attention_heads": 12,
197
+ "num_beam_groups": 1,
198
+ "num_beams": 1,
199
+ "num_codevector_groups": 2,
200
+ "num_codevectors_per_group": 320,
201
+ "num_conv_pos_embedding_groups": 16,
202
+ "num_conv_pos_embeddings": 128,
203
+ "num_feat_extract_layers": 7,
204
+ "num_hidden_layers": 6,
205
+ "num_negatives": 100,
206
+ "num_return_sequences": 1,
207
+ "output_attentions": false,
208
+ "output_hidden_size": 768,
209
+ "output_hidden_states": false,
210
+ "output_scores": false,
211
+ "pad_token_id": 0,
212
+ "prefix": null,
213
+ "problem_type": null,
214
+ "proj_codevector_dim": 256,
215
+ "pruned_heads": {},
216
+ "remove_invalid_values": false,
217
+ "repetition_penalty": 1.0,
218
+ "return_dict": true,
219
+ "return_dict_in_generate": false,
220
+ "sep_token_id": null,
221
+ "suppress_tokens": null,
222
+ "task_specific_params": null,
223
+ "tdnn_dilation": [
224
+ 1,
225
+ 2,
226
+ 3,
227
+ 1,
228
+ 1
229
+ ],
230
+ "tdnn_dim": [
231
+ 512,
232
+ 512,
233
+ 512,
234
+ 512,
235
+ 1500
236
+ ],
237
+ "tdnn_kernel": [
238
+ 5,
239
+ 3,
240
+ 3,
241
+ 1,
242
+ 1
243
+ ],
244
+ "temperature": 1.0,
245
+ "tf_legacy_loss": false,
246
+ "tie_encoder_decoder": false,
247
+ "tie_word_embeddings": true,
248
+ "tokenizer_class": null,
249
+ "top_k": 50,
250
+ "top_p": 1.0,
251
+ "torch_dtype": "float32",
252
+ "torchscript": false,
253
+ "typical_p": 1.0,
254
+ "use_bfloat16": false,
255
+ "use_weighted_layer_sum": false,
256
+ "vocab_size": 52,
257
+ "xvector_output_dim": 512
258
+ },
259
+ "eos_token_id": 0,
260
+ "is_encoder_decoder": true,
261
+ "model_type": "speech-encoder-decoder",
262
+ "pad_token_id": 0,
263
+ "tie_word_embeddings": false,
264
+ "torch_dtype": "float32",
265
+ "transformers_version": "4.45.2"
266
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6558c6372b1c09b2548a50d20d261ecc915a152d8530e3a27df1725b213c38e5
3
+ size 203847224
special_tokens_map.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|endoftext|>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|endoftext|>",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "<|endoftext|>",
17
+ "unk_token": {
18
+ "content": "<|endoftext|>",
19
+ "lstrip": false,
20
+ "normalized": true,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,22 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "0": {
6
+ "content": "<|endoftext|>",
7
+ "lstrip": false,
8
+ "normalized": true,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ }
13
+ },
14
+ "bos_token": "<|endoftext|>",
15
+ "clean_up_tokenization_spaces": false,
16
+ "eos_token": "<|endoftext|>",
17
+ "errors": "replace",
18
+ "model_max_length": 1000000000000000019884624838656,
19
+ "pad_token": "<|endoftext|>",
20
+ "tokenizer_class": "GPT2Tokenizer",
21
+ "unk_token": "<|endoftext|>"
22
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c7d0d9871518d4a96fbab122a1fa201359dc149b82a159fc77654badec35d361
3
+ size 5176
vocab.json ADDED
The diff for this file is too large to render. See raw diff