bond005 commited on
Commit
a9497ce
1 Parent(s): 9fcc3b5

Upload 7 files

Browse files
.gitattributes CHANGED
@@ -32,3 +32,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
32
  *.zip filter=lfs diff=lfs merge=lfs -text
33
  *.zst filter=lfs diff=lfs merge=lfs -text
34
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
32
  *.zip filter=lfs diff=lfs merge=lfs -text
33
  *.zst filter=lfs diff=lfs merge=lfs -text
34
  *tfevents* filter=lfs diff=lfs merge=lfs -text
35
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
config.json ADDED
@@ -0,0 +1,277 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "SpeechEncoderDecoderModel"
4
+ ],
5
+ "decoder": {
6
+ "_name_or_path": "/storage0/bi/models/mbart-large-50",
7
+ "_num_labels": 3,
8
+ "activation_dropout": 0.0,
9
+ "activation_function": "gelu",
10
+ "add_bias_logits": false,
11
+ "add_cross_attention": true,
12
+ "add_final_layer_norm": true,
13
+ "architectures": [
14
+ "MBartForConditionalGeneration"
15
+ ],
16
+ "attention_dropout": 0.1,
17
+ "bad_words_ids": null,
18
+ "bos_token_id": 0,
19
+ "chunk_size_feed_forward": 0,
20
+ "classif_dropout": 0.0,
21
+ "classifier_dropout": 0.0,
22
+ "cross_attention_hidden_size": null,
23
+ "d_model": 1024,
24
+ "decoder_attention_heads": 16,
25
+ "decoder_ffn_dim": 4096,
26
+ "decoder_layerdrop": 0.0,
27
+ "decoder_layers": 12,
28
+ "decoder_start_token_id": 2,
29
+ "diversity_penalty": 0.0,
30
+ "do_sample": false,
31
+ "dropout": 0.1,
32
+ "early_stopping": true,
33
+ "encoder_attention_heads": 16,
34
+ "encoder_ffn_dim": 4096,
35
+ "encoder_layerdrop": 0.0,
36
+ "encoder_layers": 12,
37
+ "encoder_no_repeat_ngram_size": 0,
38
+ "eos_token_id": 2,
39
+ "exponential_decay_length_penalty": null,
40
+ "finetuning_task": null,
41
+ "forced_bos_token_id": null,
42
+ "forced_eos_token_id": 2,
43
+ "gradient_checkpointing": false,
44
+ "id2label": {
45
+ "0": "LABEL_0",
46
+ "1": "LABEL_1",
47
+ "2": "LABEL_2"
48
+ },
49
+ "init_std": 0.02,
50
+ "is_decoder": true,
51
+ "is_encoder_decoder": false,
52
+ "label2id": {
53
+ "LABEL_0": 0,
54
+ "LABEL_1": 1,
55
+ "LABEL_2": 2
56
+ },
57
+ "length_penalty": 1.0,
58
+ "max_length": 200,
59
+ "max_position_embeddings": 1024,
60
+ "min_length": 0,
61
+ "model_type": "mbart",
62
+ "no_repeat_ngram_size": 0,
63
+ "normalize_before": true,
64
+ "normalize_embedding": true,
65
+ "num_beam_groups": 1,
66
+ "num_beams": 5,
67
+ "num_hidden_layers": 12,
68
+ "num_return_sequences": 1,
69
+ "output_attentions": false,
70
+ "output_hidden_states": false,
71
+ "output_past": true,
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": true,
82
+ "sep_token_id": null,
83
+ "static_position_embeddings": false,
84
+ "task_specific_params": null,
85
+ "temperature": 1.0,
86
+ "tf_legacy_loss": false,
87
+ "tie_encoder_decoder": false,
88
+ "tie_word_embeddings": true,
89
+ "tokenizer_class": "MBart50Tokenizer",
90
+ "top_k": 50,
91
+ "top_p": 1.0,
92
+ "torch_dtype": null,
93
+ "torchscript": false,
94
+ "transformers_version": "4.21.1",
95
+ "typical_p": 1.0,
96
+ "use_bfloat16": false,
97
+ "use_cache": true,
98
+ "vocab_size": 250054
99
+ },
100
+ "decoder_start_token_id": 0,
101
+ "encoder": {
102
+ "_name_or_path": "/storage0/bi/models/wav2vec2-large-ru-golos",
103
+ "activation_dropout": 0.0,
104
+ "adapter_kernel_size": 3,
105
+ "adapter_stride": 2,
106
+ "add_adapter": true,
107
+ "add_cross_attention": false,
108
+ "apply_spec_augment": true,
109
+ "architectures": [
110
+ "Wav2Vec2ForCTC"
111
+ ],
112
+ "attention_dropout": 0.1,
113
+ "bad_words_ids": null,
114
+ "bos_token_id": 1,
115
+ "chunk_size_feed_forward": 0,
116
+ "classifier_proj_size": 256,
117
+ "codevector_dim": 768,
118
+ "contrastive_logits_temperature": 0.1,
119
+ "conv_bias": true,
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": "mean",
149
+ "ctc_zero_infinity": true,
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": true,
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_dropout": 0.0,
161
+ "feat_extract_norm": "layer",
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
+ "hidden_act": "gelu",
169
+ "hidden_dropout": 0.1,
170
+ "hidden_size": 1024,
171
+ "id2label": {
172
+ "0": "LABEL_0",
173
+ "1": "LABEL_1"
174
+ },
175
+ "initializer_range": 0.02,
176
+ "intermediate_size": 4096,
177
+ "is_decoder": false,
178
+ "is_encoder_decoder": false,
179
+ "label2id": {
180
+ "LABEL_0": 0,
181
+ "LABEL_1": 1
182
+ },
183
+ "layer_norm_eps": 1e-05,
184
+ "layerdrop": 0.1,
185
+ "length_penalty": 1.0,
186
+ "mask_channel_length": 10,
187
+ "mask_channel_min_space": 1,
188
+ "mask_channel_other": 0.0,
189
+ "mask_channel_prob": 0.0,
190
+ "mask_channel_selection": "static",
191
+ "mask_feature_length": 10,
192
+ "mask_feature_min_masks": 0,
193
+ "mask_feature_prob": 0.0,
194
+ "mask_time_length": 10,
195
+ "mask_time_min_masks": 2,
196
+ "mask_time_min_space": 1,
197
+ "mask_time_other": 0.0,
198
+ "mask_time_prob": 0.05,
199
+ "mask_time_selection": "static",
200
+ "max_length": 20,
201
+ "min_length": 0,
202
+ "model_type": "wav2vec2",
203
+ "no_repeat_ngram_size": 0,
204
+ "num_adapter_layers": 3,
205
+ "num_attention_heads": 16,
206
+ "num_beam_groups": 1,
207
+ "num_beams": 1,
208
+ "num_codevector_groups": 2,
209
+ "num_codevectors_per_group": 320,
210
+ "num_conv_pos_embedding_groups": 16,
211
+ "num_conv_pos_embeddings": 128,
212
+ "num_feat_extract_layers": 7,
213
+ "num_hidden_layers": 24,
214
+ "num_negatives": 100,
215
+ "num_return_sequences": 1,
216
+ "output_attentions": false,
217
+ "output_hidden_size": 1024,
218
+ "output_hidden_states": false,
219
+ "output_scores": false,
220
+ "pad_token_id": 0,
221
+ "prefix": null,
222
+ "problem_type": null,
223
+ "proj_codevector_dim": 768,
224
+ "pruned_heads": {},
225
+ "remove_invalid_values": false,
226
+ "repetition_penalty": 1.0,
227
+ "return_dict": true,
228
+ "return_dict_in_generate": false,
229
+ "sep_token_id": null,
230
+ "task_specific_params": null,
231
+ "tdnn_dilation": [
232
+ 1,
233
+ 2,
234
+ 3,
235
+ 1,
236
+ 1
237
+ ],
238
+ "tdnn_dim": [
239
+ 512,
240
+ 512,
241
+ 512,
242
+ 512,
243
+ 1500
244
+ ],
245
+ "tdnn_kernel": [
246
+ 5,
247
+ 3,
248
+ 3,
249
+ 1,
250
+ 1
251
+ ],
252
+ "temperature": 1.0,
253
+ "tf_legacy_loss": false,
254
+ "tie_encoder_decoder": false,
255
+ "tie_word_embeddings": true,
256
+ "tokenizer_class": null,
257
+ "top_k": 50,
258
+ "top_p": 1.0,
259
+ "torch_dtype": "float32",
260
+ "torchscript": false,
261
+ "transformers_version": "4.21.1",
262
+ "typical_p": 1.0,
263
+ "use_bfloat16": false,
264
+ "use_weighted_layer_sum": false,
265
+ "vocab_size": 37,
266
+ "xvector_output_dim": 512
267
+ },
268
+ "eos_token_id": 2,
269
+ "is_encoder_decoder": true,
270
+ "max_length": 512,
271
+ "model_type": "speech-encoder-decoder",
272
+ "num_beams": 7,
273
+ "pad_token_id": 1,
274
+ "tie_word_embeddings": false,
275
+ "torch_dtype": "float32",
276
+ "transformers_version": null
277
+ }
preprocessor_config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_normalize": true,
3
+ "feature_extractor_type": "Wav2Vec2FeatureExtractor",
4
+ "feature_size": 1,
5
+ "padding_side": "right",
6
+ "padding_value": 0.0,
7
+ "processor_class": "Wav2Vec2Processor",
8
+ "return_attention_mask": true,
9
+ "sampling_rate": 16000
10
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:83d2293f2037987874ed813b1fecdefeaabf7ddff3ab599587d525a73623b7f8
3
+ size 3172211629
sentencepiece.bpe.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
3
+ size 5069051
special_tokens_map.json ADDED
@@ -0,0 +1,63 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "ar_AR",
4
+ "cs_CZ",
5
+ "de_DE",
6
+ "en_XX",
7
+ "es_XX",
8
+ "et_EE",
9
+ "fi_FI",
10
+ "fr_XX",
11
+ "gu_IN",
12
+ "hi_IN",
13
+ "it_IT",
14
+ "ja_XX",
15
+ "kk_KZ",
16
+ "ko_KR",
17
+ "lt_LT",
18
+ "lv_LV",
19
+ "my_MM",
20
+ "ne_NP",
21
+ "nl_XX",
22
+ "ro_RO",
23
+ "ru_RU",
24
+ "si_LK",
25
+ "tr_TR",
26
+ "vi_VN",
27
+ "zh_CN",
28
+ "af_ZA",
29
+ "az_AZ",
30
+ "bn_IN",
31
+ "fa_IR",
32
+ "he_IL",
33
+ "hr_HR",
34
+ "id_ID",
35
+ "ka_GE",
36
+ "km_KH",
37
+ "mk_MK",
38
+ "ml_IN",
39
+ "mn_MN",
40
+ "mr_IN",
41
+ "pl_PL",
42
+ "ps_AF",
43
+ "pt_XX",
44
+ "sv_SE",
45
+ "sw_KE",
46
+ "ta_IN",
47
+ "te_IN",
48
+ "th_TH",
49
+ "tl_XX",
50
+ "uk_UA",
51
+ "ur_PK",
52
+ "xh_ZA",
53
+ "gl_ES",
54
+ "sl_SI"
55
+ ],
56
+ "bos_token": "<s>",
57
+ "cls_token": "<s>",
58
+ "eos_token": "</s>",
59
+ "mask_token": "<mask>",
60
+ "pad_token": "<pad>",
61
+ "sep_token": "</s>",
62
+ "unk_token": "<unk>"
63
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1d58a68c276b56fcc48c165c63f70e5e4d452b4182032a5f7a2d018f4aa1a889
3
+ size 17109752
tokenizer_config.json ADDED
@@ -0,0 +1,79 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "ar_AR",
4
+ "cs_CZ",
5
+ "de_DE",
6
+ "en_XX",
7
+ "es_XX",
8
+ "et_EE",
9
+ "fi_FI",
10
+ "fr_XX",
11
+ "gu_IN",
12
+ "hi_IN",
13
+ "it_IT",
14
+ "ja_XX",
15
+ "kk_KZ",
16
+ "ko_KR",
17
+ "lt_LT",
18
+ "lv_LV",
19
+ "my_MM",
20
+ "ne_NP",
21
+ "nl_XX",
22
+ "ro_RO",
23
+ "ru_RU",
24
+ "si_LK",
25
+ "tr_TR",
26
+ "vi_VN",
27
+ "zh_CN",
28
+ "af_ZA",
29
+ "az_AZ",
30
+ "bn_IN",
31
+ "fa_IR",
32
+ "he_IL",
33
+ "hr_HR",
34
+ "id_ID",
35
+ "ka_GE",
36
+ "km_KH",
37
+ "mk_MK",
38
+ "ml_IN",
39
+ "mn_MN",
40
+ "mr_IN",
41
+ "pl_PL",
42
+ "ps_AF",
43
+ "pt_XX",
44
+ "sv_SE",
45
+ "sw_KE",
46
+ "ta_IN",
47
+ "te_IN",
48
+ "th_TH",
49
+ "tl_XX",
50
+ "uk_UA",
51
+ "ur_PK",
52
+ "xh_ZA",
53
+ "gl_ES",
54
+ "sl_SI"
55
+ ],
56
+ "bos_token": "<s>",
57
+ "cls_token": "<s>",
58
+ "eos_token": "</s>",
59
+ "mask_token": {
60
+ "__type": "AddedToken",
61
+ "content": "<mask>",
62
+ "lstrip": true,
63
+ "normalized": true,
64
+ "rstrip": false,
65
+ "single_word": false
66
+ },
67
+ "model_max_length": 1024,
68
+ "name_or_path": "/storage0/bi/models/mbart-large-50",
69
+ "pad_token": "<pad>",
70
+ "processor_class": "Wav2Vec2Processor",
71
+ "sep_token": "</s>",
72
+ "sp_model_kwargs": {},
73
+ "special_tokens_map_file": "/home/suraj/projects/mbart-50/hf_models/mbart-50-large/special_tokens_map.json",
74
+ "src_lang": null,
75
+ "tgt_lang": null,
76
+ "tokenizer_class": "MBart50Tokenizer",
77
+ "tokenizer_file": null,
78
+ "unk_token": "<unk>"
79
+ }