Hugging Face's logo

marma
/
voxrex-bart-swedish

Automatic Speech Recognition
Transformers
PyTorch
TensorBoard
speech-encoder-decoder
Inference Endpoints
Model card Files Metrics Community
KB commited on
Commit
a65356d
•
1 Parent(s): e874b4e

First

Browse files
Files changed (16) hide show
  1. config.json +276 -0
  2. preprocessor_config.json +10 -0
  3. pytorch_model.bin +3 -0
  4. runs/Mar19_23-41-42_f4f3f2f847e6/1679265723.738967/events.out.tfevents.1679265723.f4f3f2f847e6.19997.1 +3 -0
  5. runs/Mar19_23-41-42_f4f3f2f847e6/events.out.tfevents.1679265723.f4f3f2f847e6.19997.0 +3 -0
  6. runs/Mar19_23-43-30_f4f3f2f847e6/1679265830.5602849/events.out.tfevents.1679265830.f4f3f2f847e6.21425.1 +3 -0
  7. runs/Mar19_23-43-30_f4f3f2f847e6/events.out.tfevents.1679265830.f4f3f2f847e6.21425.0 +3 -0
  8. runs/Mar19_23-50-31_f4f3f2f847e6/1679266250.1373262/events.out.tfevents.1679266250.f4f3f2f847e6.23666.1 +3 -0
  9. runs/Mar19_23-50-31_f4f3f2f847e6/events.out.tfevents.1679266250.f4f3f2f847e6.23666.0 +3 -0
  10. runs/Mar19_23-53-13_f4f3f2f847e6/1679266414.4914415/events.out.tfevents.1679266414.f4f3f2f847e6.25143.1 +3 -0
  11. runs/Mar19_23-53-13_f4f3f2f847e6/events.out.tfevents.1679266414.f4f3f2f847e6.25143.0 +3 -0
  12. runs/Mar19_23-59-54_f4f3f2f847e6/1679266828.9972715/events.out.tfevents.1679266828.f4f3f2f847e6.27600.1 +3 -0
  13. runs/Mar19_23-59-54_f4f3f2f847e6/events.out.tfevents.1679266828.f4f3f2f847e6.27600.0 +3 -0
  14. special_tokens_map.json +9 -0
  15. tokenizer.json +0 -0
  16. tokenizer_config.json +14 -0
config.json ADDED
@@ -0,0 +1,276 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_commit_hash": null,
3
+ "_name_or_path": "./wav2vec2-bart-asr",
4
+ "architectures": [
5
+ "SpeechEncoderDecoderModel"
6
+ ],
7
+ "decoder": {
8
+ "_name_or_path": "KBLab/bart-base-swedish-cased",
9
+ "activation_dropout": 0.0,
10
+ "activation_function": "gelu",
11
+ "add_cross_attention": true,
12
+ "architectures": [
13
+ "BartForConditionalGeneration"
14
+ ],
15
+ "attention_dropout": 0.0,
16
+ "bad_words_ids": null,
17
+ "begin_suppress_tokens": null,
18
+ "bos_token_id": 0,
19
+ "chunk_size_feed_forward": 0,
20
+ "classifier_dropout": 0.0,
21
+ "cross_attention_hidden_size": null,
22
+ "d_model": 768,
23
+ "decoder_attention_heads": 16,
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": false,
32
+ "encoder_attention_heads": 16,
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
+ "exponential_decay_length_penalty": null,
39
+ "finetuning_task": null,
40
+ "forced_bos_token_id": null,
41
+ "forced_eos_token_id": 2,
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": 0,
61
+ "num_beam_groups": 1,
62
+ "num_beams": 1,
63
+ "num_hidden_layers": 6,
64
+ "num_return_sequences": 1,
65
+ "output_attentions": false,
66
+ "output_hidden_states": false,
67
+ "output_scores": false,
68
+ "pad_token_id": 1,
69
+ "prefix": null,
70
+ "problem_type": null,
71
+ "pruned_heads": {},
72
+ "remove_invalid_values": false,
73
+ "repetition_penalty": 1.0,
74
+ "return_dict": true,
75
+ "return_dict_in_generate": false,
76
+ "scale_embedding": false,
77
+ "sep_token_id": null,
78
+ "suppress_tokens": null,
79
+ "task_specific_params": null,
80
+ "temperature": 1.0,
81
+ "tf_legacy_loss": false,
82
+ "tie_encoder_decoder": false,
83
+ "tie_word_embeddings": true,
84
+ "tokenizer_class": null,
85
+ "top_k": 50,
86
+ "top_p": 1.0,
87
+ "torch_dtype": "float32",
88
+ "torchscript": false,
89
+ "transformers_version": "4.26.0.dev0",
90
+ "typical_p": 1.0,
91
+ "use_bfloat16": false,
92
+ "use_cache": true,
93
+ "vocab_size": 50185
94
+ },
95
+ "decoder_start_token_id": 0,
96
+ "encoder": {
97
+ "_name_or_path": "KBLab/wav2vec2-large-voxrex",
98
+ "activation_dropout": 0.0,
99
+ "adapter_kernel_size": 3,
100
+ "adapter_stride": 2,
101
+ "add_adapter": true,
102
+ "add_cross_attention": false,
103
+ "apply_spec_augment": true,
104
+ "architectures": [
105
+ "Wav2Vec2ForPreTraining"
106
+ ],
107
+ "attention_dropout": 0.1,
108
+ "bad_words_ids": null,
109
+ "begin_suppress_tokens": null,
110
+ "bos_token_id": 1,
111
+ "chunk_size_feed_forward": 0,
112
+ "classifier_proj_size": 256,
113
+ "codevector_dim": 768,
114
+ "contrastive_logits_temperature": 0.1,
115
+ "conv_bias": true,
116
+ "conv_dim": [
117
+ 512,
118
+ 512,
119
+ 512,
120
+ 512,
121
+ 512,
122
+ 512,
123
+ 512
124
+ ],
125
+ "conv_kernel": [
126
+ 10,
127
+ 3,
128
+ 3,
129
+ 3,
130
+ 3,
131
+ 2,
132
+ 2
133
+ ],
134
+ "conv_stride": [
135
+ 5,
136
+ 2,
137
+ 2,
138
+ 2,
139
+ 2,
140
+ 2,
141
+ 2
142
+ ],
143
+ "cross_attention_hidden_size": null,
144
+ "ctc_loss_reduction": "sum",
145
+ "ctc_zero_infinity": false,
146
+ "decoder_start_token_id": null,
147
+ "diversity_loss_weight": 0.1,
148
+ "diversity_penalty": 0.0,
149
+ "do_sample": false,
150
+ "do_stable_layer_norm": true,
151
+ "early_stopping": false,
152
+ "encoder_no_repeat_ngram_size": 0,
153
+ "eos_token_id": 2,
154
+ "exponential_decay_length_penalty": null,
155
+ "feat_extract_activation": "gelu",
156
+ "feat_extract_dropout": 0.0,
157
+ "feat_extract_norm": "layer",
158
+ "feat_proj_dropout": 0.0,
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": 1024,
168
+ "id2label": {
169
+ "0": "LABEL_0",
170
+ "1": "LABEL_1"
171
+ },
172
+ "initializer_range": 0.02,
173
+ "intermediate_size": 4096,
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": 0.0,
182
+ "length_penalty": 1.0,
183
+ "mask_channel_length": 10,
184
+ "mask_channel_min_space": 1,
185
+ "mask_channel_other": 0.0,
186
+ "mask_channel_prob": 0.0,
187
+ "mask_channel_selection": "static",
188
+ "mask_feature_length": 10,
189
+ "mask_feature_min_masks": 0,
190
+ "mask_feature_prob": 0.0,
191
+ "mask_time_length": 10,
192
+ "mask_time_min_masks": 2,
193
+ "mask_time_min_space": 1,
194
+ "mask_time_other": 0.0,
195
+ "mask_time_prob": 0.075,
196
+ "mask_time_selection": "static",
197
+ "max_length": 20,
198
+ "min_length": 0,
199
+ "model_type": "wav2vec2",
200
+ "no_repeat_ngram_size": 0,
201
+ "num_adapter_layers": 3,
202
+ "num_attention_heads": 16,
203
+ "num_beam_groups": 1,
204
+ "num_beams": 1,
205
+ "num_codevector_groups": 2,
206
+ "num_codevectors_per_group": 320,
207
+ "num_conv_pos_embedding_groups": 16,
208
+ "num_conv_pos_embeddings": 128,
209
+ "num_feat_extract_layers": 7,
210
+ "num_hidden_layers": 24,
211
+ "num_negatives": 100,
212
+ "num_return_sequences": 1,
213
+ "output_attentions": false,
214
+ "output_hidden_size": 1024,
215
+ "output_hidden_states": false,
216
+ "output_scores": false,
217
+ "pad_token_id": 0,
218
+ "prefix": null,
219
+ "problem_type": null,
220
+ "proj_codevector_dim": 768,
221
+ "pruned_heads": {},
222
+ "remove_invalid_values": false,
223
+ "repetition_penalty": 1.0,
224
+ "return_dict": true,
225
+ "return_dict_in_generate": false,
226
+ "sep_token_id": null,
227
+ "suppress_tokens": null,
228
+ "task_specific_params": null,
229
+ "tdnn_dilation": [
230
+ 1,
231
+ 2,
232
+ 3,
233
+ 1,
234
+ 1
235
+ ],
236
+ "tdnn_dim": [
237
+ 512,
238
+ 512,
239
+ 512,
240
+ 512,
241
+ 1500
242
+ ],
243
+ "tdnn_kernel": [
244
+ 5,
245
+ 3,
246
+ 3,
247
+ 1,
248
+ 1
249
+ ],
250
+ "temperature": 1.0,
251
+ "tf_legacy_loss": false,
252
+ "tie_encoder_decoder": false,
253
+ "tie_word_embeddings": true,
254
+ "tokenizer_class": null,
255
+ "top_k": 50,
256
+ "top_p": 1.0,
257
+ "torch_dtype": null,
258
+ "torchscript": false,
259
+ "transformers_version": "4.26.0.dev0",
260
+ "typical_p": 1.0,
261
+ "use_bfloat16": false,
262
+ "use_weighted_layer_sum": false,
263
+ "vocab_size": 32,
264
+ "xvector_output_dim": 512
265
+ },
266
+ "eos_token_id": 2,
267
+ "forced_decoder_ids": null,
268
+ "is_encoder_decoder": true,
269
+ "max_length": 200,
270
+ "model_type": "speech-encoder-decoder",
271
+ "num_beams": 5,
272
+ "pad_token_id": 1,
273
+ "tie_word_embeddings": false,
274
+ "torch_dtype": "float32",
275
+ "transformers_version": null
276
+ }
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,
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 sha256:648f6877c5cd115c2363742675510506b04999c7d0fc81b5c3c6e1af4914bf98
3
+ size 1724799429
runs/Mar19_23-41-42_f4f3f2f847e6/1679265723.738967/events.out.tfevents.1679265723.f4f3f2f847e6.19997.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cbbe2efa3144e5822ad89063db06e6343148eebe34d4076607bb9a6bebcb3ccd
3
+ size 5921
runs/Mar19_23-41-42_f4f3f2f847e6/events.out.tfevents.1679265723.f4f3f2f847e6.19997.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a37ec5d6529278ae438249da74f70389ed10406999f7214ff10a7fc41186222d
3
+ size 10179
runs/Mar19_23-43-30_f4f3f2f847e6/1679265830.5602849/events.out.tfevents.1679265830.f4f3f2f847e6.21425.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:215f06107fd11ae200fb7d522d4d442eb4b620f094cee48abd73946a2d4673d2
3
+ size 5921
runs/Mar19_23-43-30_f4f3f2f847e6/events.out.tfevents.1679265830.f4f3f2f847e6.21425.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cd70b3858e1983918a6bf3d2b09b27612a2573df71c92329c8888e7688366334
3
+ size 10179
runs/Mar19_23-50-31_f4f3f2f847e6/1679266250.1373262/events.out.tfevents.1679266250.f4f3f2f847e6.23666.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c2f13c79873b9e9fe423f82c85f7fd06cd5c0cb338ad4acf2eb383811aeb4a10
3
+ size 5921
runs/Mar19_23-50-31_f4f3f2f847e6/events.out.tfevents.1679266250.f4f3f2f847e6.23666.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:24bbe55392b98adfade2f9406dd5d2d2aee4be9058042519791ee1ca8653e5d5
3
+ size 10179
runs/Mar19_23-53-13_f4f3f2f847e6/1679266414.4914415/events.out.tfevents.1679266414.f4f3f2f847e6.25143.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:37bbd93fc5c7deab7cfc1e02980dcd05f6df720b1610282cfc87cc0f60892c3d
3
+ size 5921
runs/Mar19_23-53-13_f4f3f2f847e6/events.out.tfevents.1679266414.f4f3f2f847e6.25143.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ca1b3b267e9eb568f76ba52e1bcb1e7da9bfc2ade0626fe267ef19d4fc5983c8
3
+ size 10795
runs/Mar19_23-59-54_f4f3f2f847e6/1679266828.9972715/events.out.tfevents.1679266828.f4f3f2f847e6.27600.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3e85581b91e476e54ee70023f7ee598115e884d4587d7e00cd9942064bb271b5
3
+ size 5921
runs/Mar19_23-59-54_f4f3f2f847e6/events.out.tfevents.1679266828.f4f3f2f847e6.27600.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ee0bfdbf4f3d46f75c2b571bf20bb1a81642924be1be4c2cad604c69e423e4b0
3
+ size 53362
special_tokens_map.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "cls_token": "</s>",
4
+ "eos_token": "</s>",
5
+ "mask_token": "<mask>",
6
+ "pad_token": "<pad>",
7
+ "sep_token": "</s>",
8
+ "unk_token": "<unk>"
9
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "cls_token": "</s>",
4
+ "eos_token": "</s>",
5
+ "mask_token": "<mask>",
6
+ "model_max_length": 1000000000000000019884624838656,
7
+ "name_or_path": "./wav2vec2-bart-asr",
8
+ "pad_token": "<pad>",
9
+ "processor_class": "Wav2Vec2Processor",
10
+ "sep_token": "</s>",
11
+ "special_tokens_map_file": "/root/.cache/huggingface/hub/models--KBLab--bart-base-swedish-cased/snapshots/5e2e4b3d0b5a34f6c3e152f1b7d11fc944e27fa0/special_tokens_map.json",
12
+ "tokenizer_class": "PreTrainedTokenizerFast",
13
+ "unk_token": "<unk>"
14
+ }