patrickvonplaten commited on
Commit
1f266fa
1 Parent(s): 9f6332c
config.json ADDED
@@ -0,0 +1,244 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "SpeechEncoderDecoderModel"
4
+ ],
5
+ "decoder": {
6
+ "_name_or_path": "/home/suraj/projects/mbart-50/hf_models/mbart-50-large-one-to-many/",
7
+ "_num_labels": 3,
8
+ "activation_dropout": 0.0,
9
+ "activation_function": "relu",
10
+ "add_bias_logits": false,
11
+ "add_cross_attention": true,
12
+ "add_final_layer_norm": true,
13
+ "architectures": [
14
+ "MBartForConditionalGeneration"
15
+ ],
16
+ "attention_dropout": 0.0,
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
+ "finetuning_task": null,
40
+ "forced_bos_token_id": null,
41
+ "forced_eos_token_id": 2,
42
+ "gradient_checkpointing": false,
43
+ "id2label": {
44
+ "0": "LABEL_0",
45
+ "1": "LABEL_1",
46
+ "2": "LABEL_2"
47
+ },
48
+ "init_std": 0.02,
49
+ "is_decoder": true,
50
+ "is_encoder_decoder": true,
51
+ "label2id": {
52
+ "LABEL_0": 0,
53
+ "LABEL_1": 1,
54
+ "LABEL_2": 2
55
+ },
56
+ "length_penalty": 1.0,
57
+ "max_length": 200,
58
+ "max_position_embeddings": 1024,
59
+ "min_length": 0,
60
+ "model_type": "mbart",
61
+ "no_repeat_ngram_size": 0,
62
+ "normalize_before": true,
63
+ "normalize_embedding": true,
64
+ "num_beam_groups": 1,
65
+ "num_beams": 5,
66
+ "num_hidden_layers": 12,
67
+ "num_return_sequences": 1,
68
+ "output_attentions": false,
69
+ "output_hidden_states": false,
70
+ "output_past": true,
71
+ "output_scores": false,
72
+ "pad_token_id": 1,
73
+ "prefix": null,
74
+ "problem_type": null,
75
+ "pruned_heads": {},
76
+ "remove_invalid_values": false,
77
+ "repetition_penalty": 1.0,
78
+ "return_dict": true,
79
+ "return_dict_in_generate": false,
80
+ "scale_embedding": true,
81
+ "sep_token_id": null,
82
+ "static_position_embeddings": false,
83
+ "task_specific_params": null,
84
+ "temperature": 1.0,
85
+ "tie_encoder_decoder": false,
86
+ "tie_word_embeddings": true,
87
+ "tokenizer_class": "MBart50Tokenizer",
88
+ "top_k": 50,
89
+ "top_p": 1.0,
90
+ "torch_dtype": null,
91
+ "torchscript": false,
92
+ "transformers_version": "4.13.0.dev0",
93
+ "use_bfloat16": false,
94
+ "use_cache": true,
95
+ "vocab_size": 250054
96
+ },
97
+ "decoder_start_token_id": 2,
98
+ "encoder": {
99
+ "_name_or_path": "",
100
+ "activation_dropout": 0.0,
101
+ "adapter_kernel_size": 3,
102
+ "adapter_stride": 2,
103
+ "add_adapter": true,
104
+ "add_cross_attention": false,
105
+ "apply_spec_augment": true,
106
+ "architectures": [
107
+ "Wav2Vec2ForPreTraining"
108
+ ],
109
+ "attention_dropout": 0.1,
110
+ "bad_words_ids": null,
111
+ "bos_token_id": 1,
112
+ "chunk_size_feed_forward": 0,
113
+ "classifier_proj_size": 256,
114
+ "codevector_dim": 1024,
115
+ "contrastive_logits_temperature": 0.1,
116
+ "conv_bias": true,
117
+ "conv_dim": [
118
+ 512,
119
+ 512,
120
+ 512,
121
+ 512,
122
+ 512,
123
+ 512,
124
+ 512
125
+ ],
126
+ "conv_kernel": [
127
+ 10,
128
+ 3,
129
+ 3,
130
+ 3,
131
+ 3,
132
+ 2,
133
+ 2
134
+ ],
135
+ "conv_stride": [
136
+ 5,
137
+ 2,
138
+ 2,
139
+ 2,
140
+ 2,
141
+ 2,
142
+ 2
143
+ ],
144
+ "cross_attention_hidden_size": null,
145
+ "ctc_loss_reduction": "sum",
146
+ "ctc_zero_infinity": false,
147
+ "decoder_start_token_id": null,
148
+ "diversity_loss_weight": 0.1,
149
+ "diversity_penalty": 0.0,
150
+ "do_sample": false,
151
+ "do_stable_layer_norm": true,
152
+ "early_stopping": false,
153
+ "encoder_no_repeat_ngram_size": 0,
154
+ "eos_token_id": 2,
155
+ "feat_extract_activation": "gelu",
156
+ "feat_extract_dropout": 0.0,
157
+ "feat_extract_norm": "layer",
158
+ "feat_proj_dropout": 0.1,
159
+ "feat_quantizer_dropout": 0.0,
160
+ "final_dropout": 0.0,
161
+ "finetuning_task": null,
162
+ "forced_bos_token_id": null,
163
+ "forced_eos_token_id": null,
164
+ "gradient_checkpointing": false,
165
+ "hidden_act": "gelu",
166
+ "hidden_dropout": 0.1,
167
+ "hidden_size": 1920,
168
+ "id2label": {
169
+ "0": "LABEL_0",
170
+ "1": "LABEL_1"
171
+ },
172
+ "initializer_range": 0.02,
173
+ "intermediate_size": 7680,
174
+ "is_decoder": false,
175
+ "is_encoder_decoder": false,
176
+ "label2id": {
177
+ "LABEL_0": 0,
178
+ "LABEL_1": 1
179
+ },
180
+ "layer_norm_eps": 1e-05,
181
+ "layerdrop": 0.1,
182
+ "length_penalty": 1.0,
183
+ "mask_feature_length": 10,
184
+ "mask_feature_prob": 0.0,
185
+ "mask_time_length": 10,
186
+ "mask_time_prob": 0.075,
187
+ "max_length": 20,
188
+ "min_length": 0,
189
+ "model_type": "wav2vec2",
190
+ "no_repeat_ngram_size": 0,
191
+ "num_adapter_layers": 3,
192
+ "num_attention_heads": 16,
193
+ "num_beam_groups": 1,
194
+ "num_beams": 1,
195
+ "num_codevector_groups": 2,
196
+ "num_codevectors_per_group": 320,
197
+ "num_conv_pos_embedding_groups": 16,
198
+ "num_conv_pos_embeddings": 128,
199
+ "num_feat_extract_layers": 7,
200
+ "num_hidden_layers": 48,
201
+ "num_negatives": 100,
202
+ "num_return_sequences": 1,
203
+ "output_attentions": false,
204
+ "output_hidden_size": 1024,
205
+ "output_hidden_states": false,
206
+ "output_scores": false,
207
+ "pad_token_id": 0,
208
+ "prefix": null,
209
+ "problem_type": null,
210
+ "proj_codevector_dim": 1024,
211
+ "pruned_heads": {},
212
+ "remove_invalid_values": false,
213
+ "repetition_penalty": 1.0,
214
+ "return_dict": true,
215
+ "return_dict_in_generate": false,
216
+ "sep_token_id": null,
217
+ "task_specific_params": null,
218
+ "temperature": 1.0,
219
+ "tie_encoder_decoder": false,
220
+ "tie_word_embeddings": true,
221
+ "tokenizer_class": null,
222
+ "top_k": 50,
223
+ "top_p": 1.0,
224
+ "torch_dtype": "float32",
225
+ "torchscript": false,
226
+ "transformers_version": "4.13.0.dev0",
227
+ "use_bfloat16": false,
228
+ "use_weighted_layer_sum": false,
229
+ "vocab_size": 32
230
+ },
231
+ "eos_token_id": 2,
232
+ "feature_extractor_type": "wav2vec2",
233
+ "forced_bos_token_id": 250004,
234
+ "forced_eos_token_id": 2,
235
+ "is_encoder_decoder": true,
236
+ "max_length": 200,
237
+ "model_type": "speech-encoder-decoder",
238
+ "num_beams": 5,
239
+ "pad_token_id": 1,
240
+ "tie_word_embeddings": false,
241
+ "tokenizer_class": "mbart50",
242
+ "torch_dtype": "float32",
243
+ "transformers_version": null
244
+ }
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,
7
+ "return_attention_mask": true,
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:f50338dac82de54f2279eef31255e7105bc264b5ec459e5ed1c9c292c80ae1cf
3
+ size 10555582361
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 @@
 
 
1
+ {"eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "<s>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true}, "additional_special_tokens": ["ar_AR", "cs_CZ", "de_DE", "en_XX", "es_XX", "et_EE", "fi_FI", "fr_XX", "gu_IN", "hi_IN", "it_IT", "ja_XX", "kk_KZ", "ko_KR", "lt_LT", "lv_LV", "my_MM", "ne_NP", "nl_XX", "ro_RO", "ru_RU", "si_LK", "tr_TR", "vi_VN", "zh_CN", "af_ZA", "az_AZ", "bn_IN", "fa_IR", "he_IL", "hr_HR", "id_ID", "ka_GE", "km_KH", "mk_MK", "ml_IN", "mn_MN", "mr_IN", "pl_PL", "ps_AF", "pt_XX", "sv_SE", "sw_KE", "ta_IN", "te_IN", "th_TH", "tl_XX", "uk_UA", "ur_PK", "xh_ZA", "gl_ES", "sl_SI"]}
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"src_lang": null, "tgt_lang": null, "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "cls_token": "<s>", "pad_token": "<pad>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "sp_model_kwargs": {}, "additional_special_tokens": ["ar_AR", "cs_CZ", "de_DE", "en_XX", "es_XX", "et_EE", "fi_FI", "fr_XX", "gu_IN", "hi_IN", "it_IT", "ja_XX", "kk_KZ", "ko_KR", "lt_LT", "lv_LV", "my_MM", "ne_NP", "nl_XX", "ro_RO", "ru_RU", "si_LK", "tr_TR", "vi_VN", "zh_CN", "af_ZA", "az_AZ", "bn_IN", "fa_IR", "he_IL", "hr_HR", "id_ID", "ka_GE", "km_KH", "mk_MK", "ml_IN", "mn_MN", "mr_IN", "pl_PL", "ps_AF", "pt_XX", "sv_SE", "sw_KE", "ta_IN", "te_IN", "th_TH", "tl_XX", "uk_UA", "ur_PK", "xh_ZA", "gl_ES", "sl_SI"], "tokenizer_class": "MBart50Tokenizer"}