ngdiana commited on
Commit
7a3fd2a
1 Parent(s): 29a51c0

upload model files

Browse files
config.json ADDED
@@ -0,0 +1,281 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "SpeechEncoderDecoderModel"
4
+ ],
5
+ "decoder": {
6
+ "_name_or_path": "facebook/bart-base",
7
+ "activation_dropout": 0.1,
8
+ "activation_function": "gelu",
9
+ "add_bias_logits": false,
10
+ "add_cross_attention": true,
11
+ "add_final_layer_norm": false,
12
+ "architectures": [
13
+ "BartModel"
14
+ ],
15
+ "attention_dropout": 0.1,
16
+ "bad_words_ids": null,
17
+ "bos_token_id": 0,
18
+ "chunk_size_feed_forward": 0,
19
+ "classif_dropout": 0.1,
20
+ "classifier_dropout": 0.0,
21
+ "cross_attention_hidden_size": null,
22
+ "d_model": 768,
23
+ "decoder_attention_heads": 12,
24
+ "decoder_ffn_dim": 3072,
25
+ "decoder_layerdrop": 0.0,
26
+ "decoder_layers": 6,
27
+ "decoder_start_token_id": 2,
28
+ "diversity_penalty": 0.0,
29
+ "do_sample": false,
30
+ "dropout": 0.1,
31
+ "early_stopping": true,
32
+ "encoder_attention_heads": 12,
33
+ "encoder_ffn_dim": 3072,
34
+ "encoder_layerdrop": 0.0,
35
+ "encoder_layers": 6,
36
+ "encoder_no_repeat_ngram_size": 0,
37
+ "eos_token_id": 2,
38
+ "finetuning_task": null,
39
+ "forced_bos_token_id": null,
40
+ "forced_eos_token_id": 2,
41
+ "gradient_checkpointing": false,
42
+ "id2label": {
43
+ "0": "LABEL_0",
44
+ "1": "LABEL_1",
45
+ "2": "LABEL_2"
46
+ },
47
+ "init_std": 0.02,
48
+ "is_decoder": true,
49
+ "is_encoder_decoder": false,
50
+ "label2id": {
51
+ "LABEL_0": 0,
52
+ "LABEL_1": 1,
53
+ "LABEL_2": 2
54
+ },
55
+ "length_penalty": 1.0,
56
+ "max_length": 20,
57
+ "max_position_embeddings": 1024,
58
+ "min_length": 0,
59
+ "model_type": "bart",
60
+ "no_repeat_ngram_size": 3,
61
+ "normalize_before": false,
62
+ "normalize_embedding": true,
63
+ "num_beam_groups": 1,
64
+ "num_beams": 4,
65
+ "num_hidden_layers": 6,
66
+ "num_return_sequences": 1,
67
+ "output_attentions": false,
68
+ "output_hidden_states": false,
69
+ "output_scores": false,
70
+ "pad_token_id": 1,
71
+ "prefix": null,
72
+ "problem_type": null,
73
+ "pruned_heads": {},
74
+ "remove_invalid_values": false,
75
+ "repetition_penalty": 1.0,
76
+ "return_dict": true,
77
+ "return_dict_in_generate": false,
78
+ "scale_embedding": false,
79
+ "sep_token_id": null,
80
+ "task_specific_params": {
81
+ "summarization": {
82
+ "length_penalty": 1.0,
83
+ "max_length": 128,
84
+ "min_length": 12,
85
+ "num_beams": 4
86
+ },
87
+ "summarization_cnn": {
88
+ "length_penalty": 2.0,
89
+ "max_length": 142,
90
+ "min_length": 56,
91
+ "num_beams": 4
92
+ },
93
+ "summarization_xsum": {
94
+ "length_penalty": 1.0,
95
+ "max_length": 62,
96
+ "min_length": 11,
97
+ "num_beams": 6
98
+ }
99
+ },
100
+ "temperature": 1.0,
101
+ "tie_encoder_decoder": false,
102
+ "tie_word_embeddings": true,
103
+ "tokenizer_class": null,
104
+ "top_k": 50,
105
+ "top_p": 1.0,
106
+ "torch_dtype": "float32",
107
+ "torchscript": false,
108
+ "transformers_version": "4.16.2",
109
+ "use_bfloat16": false,
110
+ "use_cache": true,
111
+ "vocab_size": 50265
112
+ },
113
+ "decoder_start_token_id": 0,
114
+ "encoder": {
115
+ "_name_or_path": "facebook/wav2vec2-large-xlsr-53-german",
116
+ "activation_dropout": 0.1,
117
+ "adapter_kernel_size": 3,
118
+ "adapter_stride": 2,
119
+ "add_adapter": true,
120
+ "add_cross_attention": false,
121
+ "apply_spec_augment": true,
122
+ "architectures": [
123
+ "Wav2Vec2ForCTC"
124
+ ],
125
+ "attention_dropout": 0.1,
126
+ "bad_words_ids": null,
127
+ "bos_token_id": 1,
128
+ "chunk_size_feed_forward": 0,
129
+ "classifier_proj_size": 256,
130
+ "codevector_dim": 256,
131
+ "contrastive_logits_temperature": 0.1,
132
+ "conv_bias": true,
133
+ "conv_dim": [
134
+ 512,
135
+ 512,
136
+ 512,
137
+ 512,
138
+ 512,
139
+ 512,
140
+ 512
141
+ ],
142
+ "conv_kernel": [
143
+ 10,
144
+ 3,
145
+ 3,
146
+ 3,
147
+ 3,
148
+ 2,
149
+ 2
150
+ ],
151
+ "conv_stride": [
152
+ 5,
153
+ 2,
154
+ 2,
155
+ 2,
156
+ 2,
157
+ 2,
158
+ 2
159
+ ],
160
+ "cross_attention_hidden_size": null,
161
+ "ctc_loss_reduction": "sum",
162
+ "ctc_zero_infinity": false,
163
+ "decoder_start_token_id": null,
164
+ "diversity_loss_weight": 0.1,
165
+ "diversity_penalty": 0.0,
166
+ "do_sample": false,
167
+ "do_stable_layer_norm": true,
168
+ "early_stopping": false,
169
+ "encoder_no_repeat_ngram_size": 0,
170
+ "eos_token_id": 2,
171
+ "feat_extract_activation": "gelu",
172
+ "feat_extract_dropout": 0.0,
173
+ "feat_extract_norm": "layer",
174
+ "feat_proj_dropout": 0.0,
175
+ "feat_quantizer_dropout": 0.0,
176
+ "final_dropout": 0.1,
177
+ "finetuning_task": null,
178
+ "forced_bos_token_id": null,
179
+ "forced_eos_token_id": null,
180
+ "gradient_checkpointing": false,
181
+ "hidden_act": "gelu",
182
+ "hidden_dropout": 0.1,
183
+ "hidden_dropout_prob": 0.1,
184
+ "hidden_size": 1024,
185
+ "id2label": {
186
+ "0": "LABEL_0",
187
+ "1": "LABEL_1"
188
+ },
189
+ "initializer_range": 0.02,
190
+ "intermediate_size": 4096,
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": 0.0,
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": 0.05,
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": 16,
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": 24,
220
+ "num_negatives": 100,
221
+ "num_return_sequences": 1,
222
+ "output_attentions": false,
223
+ "output_hidden_size": 1024,
224
+ "output_hidden_states": false,
225
+ "output_scores": false,
226
+ "pad_token_id": 0,
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
+ "task_specific_params": null,
237
+ "tdnn_dilation": [
238
+ 1,
239
+ 2,
240
+ 3,
241
+ 1,
242
+ 1
243
+ ],
244
+ "tdnn_dim": [
245
+ 512,
246
+ 512,
247
+ 512,
248
+ 512,
249
+ 1500
250
+ ],
251
+ "tdnn_kernel": [
252
+ 5,
253
+ 3,
254
+ 3,
255
+ 1,
256
+ 1
257
+ ],
258
+ "temperature": 1.0,
259
+ "tie_encoder_decoder": false,
260
+ "tie_word_embeddings": true,
261
+ "tokenizer_class": null,
262
+ "top_k": 50,
263
+ "top_p": 1.0,
264
+ "torch_dtype": null,
265
+ "torchscript": false,
266
+ "transformers_version": "4.16.2",
267
+ "use_bfloat16": false,
268
+ "use_weighted_layer_sum": false,
269
+ "vocab_size": 36,
270
+ "xvector_output_dim": 512
271
+ },
272
+ "eos_token_id": 2,
273
+ "is_encoder_decoder": true,
274
+ "max_length": 200,
275
+ "model_type": "speech-encoder-decoder",
276
+ "num_beams": 5,
277
+ "pad_token_id": 1,
278
+ "tie_word_embeddings": false,
279
+ "torch_dtype": "float32",
280
+ "transformers_version": null
281
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
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:bd0208723f5b30f9b3c804fbe1df9d7c65431677e053641332e6690775bcf616
3
+ size 1725064805
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"bos_token": "<s>", "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": false}}
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"unk_token": "<unk>", "bos_token": "<s>", "eos_token": "</s>", "add_prefix_space": false, "errors": "replace", "sep_token": "</s>", "cls_token": "<s>", "pad_token": "<pad>", "mask_token": "<mask>", "trim_offsets": true, "model_max_length": 1024, "special_tokens_map_file": null, "name_or_path": "facebook/bart-base", "tokenizer_class": "BartTokenizer", "processor_class": "Wav2Vec2Processor"}
vocab.json ADDED
The diff for this file is too large to render. See raw diff