Hugging Face's logo

TheRamsay
/
wav2vec2-gpt2-scratch-60M-parczech-2

Safetensors
speech-encoder-decoder
Model card Files
xet
Community
TheRamsay commited on
Commit
57fd78e
·
verified ·
1 Parent(s): fddf693

Training in progress, step 2500

Browse files
Files changed (4) hide show
  1. config.json +281 -0
  2. model.safetensors +3 -0
  3. preprocessor_config.json +10 -0
  4. training_args.bin +3 -0
config.json ADDED
@@ -0,0 +1,281 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "SpeechEncoderDecoderModel"
4
+ ],
5
+ "bos_token_id": 50000,
6
+ "decoder": {
7
+ "_attn_implementation_autoset": false,
8
+ "_name_or_path": "fav-kky/gpt2-small-cs",
9
+ "activation_function": "gelu",
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": 50000,
18
+ "chunk_size_feed_forward": 0,
19
+ "cross_attention_hidden_size": null,
20
+ "decoder_ignore_mismatched_sizes": true,
21
+ "decoder_start_token_id": 50000,
22
+ "decoder_vocab_size": 50002,
23
+ "diversity_penalty": 0.0,
24
+ "do_sample": false,
25
+ "early_stopping": false,
26
+ "embd_pdrop": 0.1,
27
+ "encoder_ctc_loss_reduction": "mean",
28
+ "encoder_layerdrop": 0.0,
29
+ "encoder_no_repeat_ngram_size": 0,
30
+ "encoder_pad_token_id": 50001,
31
+ "encoder_vocab_size": 50002,
32
+ "eos_token_id": 0,
33
+ "exponential_decay_length_penalty": null,
34
+ "finetuning_task": null,
35
+ "forced_bos_token_id": null,
36
+ "forced_eos_token_id": null,
37
+ "gradient_checkpointing": false,
38
+ "id2label": {
39
+ "0": "LABEL_0",
40
+ "1": "LABEL_1"
41
+ },
42
+ "initializer_range": 0.02,
43
+ "is_decoder": true,
44
+ "is_encoder_decoder": false,
45
+ "label2id": {
46
+ "LABEL_0": 0,
47
+ "LABEL_1": 1
48
+ },
49
+ "layer_norm_epsilon": 1e-05,
50
+ "length_penalty": 1.0,
51
+ "max_length": 20,
52
+ "min_length": 0,
53
+ "model_type": "gpt2",
54
+ "n_ctx": 1024,
55
+ "n_embd": 512,
56
+ "n_head": 8,
57
+ "n_inner": null,
58
+ "n_layer": 4,
59
+ "n_positions": 1024,
60
+ "no_repeat_ngram_size": 0,
61
+ "num_beam_groups": 1,
62
+ "num_beams": 1,
63
+ "num_return_sequences": 1,
64
+ "output_attentions": false,
65
+ "output_hidden_states": false,
66
+ "output_scores": false,
67
+ "pad_token_id": 50001,
68
+ "prefix": null,
69
+ "problem_type": null,
70
+ "pruned_heads": {},
71
+ "remove_invalid_values": false,
72
+ "reorder_and_upcast_attn": false,
73
+ "repetition_penalty": 1.0,
74
+ "resid_pdrop": 0.1,
75
+ "return_dict": true,
76
+ "return_dict_in_generate": false,
77
+ "scale_attn_by_inverse_layer_idx": false,
78
+ "scale_attn_weights": true,
79
+ "sep_token_id": null,
80
+ "summary_activation": null,
81
+ "summary_first_dropout": 0.1,
82
+ "summary_proj_to_labels": true,
83
+ "summary_type": "cls_index",
84
+ "summary_use_proj": true,
85
+ "suppress_tokens": null,
86
+ "task_specific_params": {
87
+ "text-generation": {
88
+ "do_sample": true,
89
+ "max_length": 1024
90
+ }
91
+ },
92
+ "temperature": 1.0,
93
+ "tf_legacy_loss": false,
94
+ "tie_encoder_decoder": false,
95
+ "tie_word_embeddings": true,
96
+ "tokenizer_class": null,
97
+ "top_k": 50,
98
+ "top_p": 1.0,
99
+ "torch_dtype": "float32",
100
+ "torchscript": false,
101
+ "typical_p": 1.0,
102
+ "use_bfloat16": false,
103
+ "use_cache": true,
104
+ "vocab_size": 50002
105
+ },
106
+ "decoder_start_token_id": 50000,
107
+ "encoder": {
108
+ "_attn_implementation_autoset": false,
109
+ "_name_or_path": "TheRamsay/wav2vec2-pretraining-parczech-20M",
110
+ "activation_dropout": 0.1,
111
+ "adapter_attn_dim": null,
112
+ "adapter_kernel_size": 3,
113
+ "adapter_stride": 2,
114
+ "add_adapter": false,
115
+ "add_cross_attention": false,
116
+ "apply_spec_augment": true,
117
+ "architectures": [
118
+ "Wav2Vec2ForPreTraining"
119
+ ],
120
+ "attention_dropout": 0.1,
121
+ "bad_words_ids": null,
122
+ "begin_suppress_tokens": null,
123
+ "bos_token_id": 50000,
124
+ "chunk_size_feed_forward": 0,
125
+ "classifier_proj_size": 256,
126
+ "codevector_dim": 256,
127
+ "contrastive_logits_temperature": 0.1,
128
+ "conv_bias": false,
129
+ "conv_dim": [
130
+ 512,
131
+ 512,
132
+ 512,
133
+ 512,
134
+ 512,
135
+ 512,
136
+ 512
137
+ ],
138
+ "conv_kernel": [
139
+ 10,
140
+ 3,
141
+ 3,
142
+ 3,
143
+ 3,
144
+ 2,
145
+ 2
146
+ ],
147
+ "conv_stride": [
148
+ 5,
149
+ 2,
150
+ 2,
151
+ 2,
152
+ 2,
153
+ 2,
154
+ 2
155
+ ],
156
+ "cross_attention_hidden_size": null,
157
+ "ctc_loss_reduction": "sum",
158
+ "ctc_zero_infinity": false,
159
+ "decoder_ignore_mismatched_sizes": true,
160
+ "decoder_start_token_id": null,
161
+ "decoder_vocab_size": 50002,
162
+ "diversity_loss_weight": 0.1,
163
+ "diversity_penalty": 0.0,
164
+ "do_sample": false,
165
+ "do_stable_layer_norm": false,
166
+ "early_stopping": false,
167
+ "encoder_ctc_loss_reduction": "mean",
168
+ "encoder_layerdrop": 0.0,
169
+ "encoder_no_repeat_ngram_size": 0,
170
+ "encoder_pad_token_id": 50001,
171
+ "encoder_vocab_size": 50002,
172
+ "eos_token_id": 0,
173
+ "exponential_decay_length_penalty": null,
174
+ "feat_extract_activation": "gelu",
175
+ "feat_extract_norm": "group",
176
+ "feat_proj_dropout": 0.0,
177
+ "feat_quantizer_dropout": 0.0,
178
+ "final_dropout": 0.1,
179
+ "finetuning_task": null,
180
+ "forced_bos_token_id": null,
181
+ "forced_eos_token_id": null,
182
+ "hidden_act": "gelu",
183
+ "hidden_dropout": 0.1,
184
+ "hidden_size": 768,
185
+ "id2label": {
186
+ "0": "LABEL_0",
187
+ "1": "LABEL_1"
188
+ },
189
+ "initializer_range": 0.02,
190
+ "intermediate_size": 3072,
191
+ "is_decoder": false,
192
+ "is_encoder_decoder": false,
193
+ "label2id": {
194
+ "LABEL_0": 0,
195
+ "LABEL_1": 1
196
+ },
197
+ "layer_norm_eps": 1e-05,
198
+ "layerdrop": 0.1,
199
+ "length_penalty": 1.0,
200
+ "mask_feature_length": 10,
201
+ "mask_feature_min_masks": 0,
202
+ "mask_feature_prob": 0.0,
203
+ "mask_time_length": 10,
204
+ "mask_time_min_masks": 2,
205
+ "mask_time_prob": 0.0,
206
+ "max_length": 20,
207
+ "min_length": 0,
208
+ "model_type": "wav2vec2",
209
+ "no_repeat_ngram_size": 0,
210
+ "num_adapter_layers": 3,
211
+ "num_attention_heads": 12,
212
+ "num_beam_groups": 1,
213
+ "num_beams": 1,
214
+ "num_codevector_groups": 2,
215
+ "num_codevectors_per_group": 320,
216
+ "num_conv_pos_embedding_groups": 16,
217
+ "num_conv_pos_embeddings": 128,
218
+ "num_feat_extract_layers": 7,
219
+ "num_hidden_layers": 3,
220
+ "num_negatives": 100,
221
+ "num_return_sequences": 1,
222
+ "output_attentions": false,
223
+ "output_hidden_size": 768,
224
+ "output_hidden_states": false,
225
+ "output_scores": false,
226
+ "pad_token_id": 50001,
227
+ "prefix": null,
228
+ "problem_type": null,
229
+ "proj_codevector_dim": 256,
230
+ "pruned_heads": {},
231
+ "remove_invalid_values": false,
232
+ "repetition_penalty": 1.0,
233
+ "return_dict": true,
234
+ "return_dict_in_generate": false,
235
+ "sep_token_id": null,
236
+ "suppress_tokens": null,
237
+ "task_specific_params": null,
238
+ "tdnn_dilation": [
239
+ 1,
240
+ 2,
241
+ 3,
242
+ 1,
243
+ 1
244
+ ],
245
+ "tdnn_dim": [
246
+ 512,
247
+ 512,
248
+ 512,
249
+ 512,
250
+ 1500
251
+ ],
252
+ "tdnn_kernel": [
253
+ 5,
254
+ 3,
255
+ 3,
256
+ 1,
257
+ 1
258
+ ],
259
+ "temperature": 1.0,
260
+ "tf_legacy_loss": false,
261
+ "tie_encoder_decoder": false,
262
+ "tie_word_embeddings": true,
263
+ "tokenizer_class": null,
264
+ "top_k": 50,
265
+ "top_p": 1.0,
266
+ "torch_dtype": "float32",
267
+ "torchscript": false,
268
+ "typical_p": 1.0,
269
+ "use_bfloat16": false,
270
+ "use_weighted_layer_sum": false,
271
+ "vocab_size": 32,
272
+ "xvector_output_dim": 512
273
+ },
274
+ "eos_token_id": 0,
275
+ "is_encoder_decoder": true,
276
+ "model_type": "speech-encoder-decoder",
277
+ "pad_token_id": 50001,
278
+ "tie_word_embeddings": false,
279
+ "torch_dtype": "float32",
280
+ "transformers_version": "4.49.0"
281
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3eb23fbbf51fe668ec26efe2b4c6cea882511cf4a93385fc337437cb0ed9e737
3
+ size 295682728
preprocessor_config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_normalize": true,
3
+ "feature_dim": 1,
4
+ "feature_extractor_type": "Wav2Vec2FeatureExtractor",
5
+ "feature_size": 1,
6
+ "padding_side": "right",
7
+ "padding_value": 0.0,
8
+ "return_attention_mask": true,
9
+ "sampling_rate": 16000
10
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cca1a8d8ee90941fb1f6f415d3fed1d5e34635eba3a865b6d1a33f5d82799165
3
+ size 5624