Aditya02 commited on
Commit
9b7cfa3
·
verified ·
1 Parent(s): b46b469

Upload folder using huggingface_hub

Browse files
README.md CHANGED
@@ -1,3 +0,0 @@
1
- ---
2
- license: apache-2.0
3
- ---
 
 
 
 
generation_config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 4,
4
+ "decoder_start_token_id": 13764,
5
+ "eos_token_id": 3,
6
+ "output_attentions": false,
7
+ "output_hidden_states": false,
8
+ "pad_token_id": 2,
9
+ "transformers_version": "5.12.1"
10
+ }
openvino_decoder_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5efa3a36121553f0c2a182909db9b5ec79c2837eca580cf193b275e016ad866f
3
+ size 307062915
openvino_decoder_model.xml ADDED
The diff for this file is too large to render. See raw diff
 
openvino_decoder_with_past_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6f7d508a4979aab917d65da2affe0df14106a0ef572e4c98211a625ff223137f
3
+ size 273475713
openvino_decoder_with_past_model.xml ADDED
The diff for this file is too large to render. See raw diff
 
openvino_encoder_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2d4ac3b21994b6116291aac5cf1b00b6b6baf800041d5c3cd870e7221f1a87c9
3
+ size 3790434378
openvino_encoder_model.xml ADDED
The diff for this file is too large to render. See raw diff
 
ov_cohere_transcribe_kvcache.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "model_id": "CohereLabs/cohere-transcribe-03-2026",
3
+ "sampling_rate": 16000,
4
+ "n_mels": 128,
5
+ "num_layers": 8,
6
+ "num_kv_heads": 8,
7
+ "head_dim": 128,
8
+ "encoder_hidden": 1280,
9
+ "vocab_size": 16384,
10
+ "eos_token_id": 3,
11
+ "pad_token_id": 2,
12
+ "bos_token_id": 4,
13
+ "encoder_ir": "openvino_encoder_model.xml",
14
+ "decoder_ir": "openvino_decoder_model.xml",
15
+ "decoder_with_past_ir": "openvino_decoder_with_past_model.xml"
16
+ }
processor_config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "feature_extractor": {
3
+ "auto_map": {
4
+ "AutoFeatureExtractor": "processing_cohere_asr.CohereAsrFeatureExtractor"
5
+ },
6
+ "dither": 1e-05,
7
+ "feature_extractor_type": "CohereAsrFeatureExtractor",
8
+ "feature_size": 128,
9
+ "frame_splicing": 1,
10
+ "hop_length": 160,
11
+ "log": true,
12
+ "max_audio_clip_s": 35.0,
13
+ "min_energy_window_samples": 1600,
14
+ "n_fft": 512,
15
+ "n_window_size": 400,
16
+ "n_window_stride": 160,
17
+ "normalize": "per_feature",
18
+ "overlap_chunk_second": 5.0,
19
+ "pad_to": 0,
20
+ "padding_side": "right",
21
+ "padding_value": 0.0,
22
+ "preemphasis": 0.97,
23
+ "return_attention_mask": true,
24
+ "sampling_rate": 16000,
25
+ "win_length": 400
26
+ },
27
+ "processor_class": "CohereAsrProcessor"
28
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,275 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "auto_map": {
4
+ "AutoTokenizer": [
5
+ "tokenization_cohere_asr.CohereAsrTokenizer",
6
+ null
7
+ ]
8
+ },
9
+ "backend": "tokenizers",
10
+ "bos_token": "<|startoftranscript|>",
11
+ "clean_up_tokenization_spaces": false,
12
+ "eos_token": "<|endoftext|>",
13
+ "extra_special_tokens": [
14
+ "<|nospeech|>",
15
+ "<|pnc|>",
16
+ "<|nopnc|>",
17
+ "<|startofcontext|>",
18
+ "<|itn|>",
19
+ "<|noitn|>",
20
+ "<|timestamp|>",
21
+ "<|notimestamp|>",
22
+ "<|diarize|>",
23
+ "<|nodiarize|>",
24
+ "<|spkchange|>",
25
+ "<|audioseparator|>",
26
+ "<|emo:undefined|>",
27
+ "<|emo:neutral|>",
28
+ "<|emo:happy|>",
29
+ "<|emo:sad|>",
30
+ "<|emo:angry|>",
31
+ "<|unklang|>",
32
+ "<|aa|>",
33
+ "<|ab|>",
34
+ "<|af|>",
35
+ "<|ak|>",
36
+ "<|sq|>",
37
+ "<|am|>",
38
+ "<|ar|>",
39
+ "<|an|>",
40
+ "<|hy|>",
41
+ "<|as|>",
42
+ "<|av|>",
43
+ "<|ae|>",
44
+ "<|ay|>",
45
+ "<|az|>",
46
+ "<|bm|>",
47
+ "<|ba|>",
48
+ "<|eu|>",
49
+ "<|be|>",
50
+ "<|bn|>",
51
+ "<|bi|>",
52
+ "<|bs|>",
53
+ "<|br|>",
54
+ "<|bg|>",
55
+ "<|my|>",
56
+ "<|ca|>",
57
+ "<|ch|>",
58
+ "<|ce|>",
59
+ "<|ny|>",
60
+ "<|zh|>",
61
+ "<|cu|>",
62
+ "<|cv|>",
63
+ "<|kw|>",
64
+ "<|co|>",
65
+ "<|cr|>",
66
+ "<|hr|>",
67
+ "<|cs|>",
68
+ "<|da|>",
69
+ "<|dv|>",
70
+ "<|nl|>",
71
+ "<|dz|>",
72
+ "<|en|>",
73
+ "<|eo|>",
74
+ "<|et|>",
75
+ "<|ee|>",
76
+ "<|fo|>",
77
+ "<|fj|>",
78
+ "<|fi|>",
79
+ "<|fr|>",
80
+ "<|fy|>",
81
+ "<|ff|>",
82
+ "<|gd|>",
83
+ "<|gl|>",
84
+ "<|lg|>",
85
+ "<|ka|>",
86
+ "<|de|>",
87
+ "<|el|>",
88
+ "<|kl|>",
89
+ "<|gn|>",
90
+ "<|gu|>",
91
+ "<|ht|>",
92
+ "<|ha|>",
93
+ "<|he|>",
94
+ "<|hz|>",
95
+ "<|hi|>",
96
+ "<|ho|>",
97
+ "<|hu|>",
98
+ "<|is|>",
99
+ "<|io|>",
100
+ "<|ig|>",
101
+ "<|id|>",
102
+ "<|ia|>",
103
+ "<|ie|>",
104
+ "<|iu|>",
105
+ "<|ik|>",
106
+ "<|ga|>",
107
+ "<|it|>",
108
+ "<|ja|>",
109
+ "<|jv|>",
110
+ "<|kn|>",
111
+ "<|kr|>",
112
+ "<|ks|>",
113
+ "<|kk|>",
114
+ "<|km|>",
115
+ "<|ki|>",
116
+ "<|rw|>",
117
+ "<|ky|>",
118
+ "<|kv|>",
119
+ "<|kg|>",
120
+ "<|ko|>",
121
+ "<|kj|>",
122
+ "<|ku|>",
123
+ "<|lo|>",
124
+ "<|la|>",
125
+ "<|lv|>",
126
+ "<|li|>",
127
+ "<|ln|>",
128
+ "<|lt|>",
129
+ "<|lu|>",
130
+ "<|lb|>",
131
+ "<|mk|>",
132
+ "<|mg|>",
133
+ "<|ms|>",
134
+ "<|ml|>",
135
+ "<|mt|>",
136
+ "<|gv|>",
137
+ "<|mi|>",
138
+ "<|mr|>",
139
+ "<|mh|>",
140
+ "<|mn|>",
141
+ "<|na|>",
142
+ "<|nv|>",
143
+ "<|nd|>",
144
+ "<|nr|>",
145
+ "<|ng|>",
146
+ "<|ne|>",
147
+ "<|no|>",
148
+ "<|nb|>",
149
+ "<|nn|>",
150
+ "<|oc|>",
151
+ "<|oj|>",
152
+ "<|or|>",
153
+ "<|om|>",
154
+ "<|os|>",
155
+ "<|pi|>",
156
+ "<|ps|>",
157
+ "<|fa|>",
158
+ "<|pl|>",
159
+ "<|pt|>",
160
+ "<|pa|>",
161
+ "<|qu|>",
162
+ "<|ro|>",
163
+ "<|rm|>",
164
+ "<|rn|>",
165
+ "<|ru|>",
166
+ "<|se|>",
167
+ "<|sm|>",
168
+ "<|sg|>",
169
+ "<|sa|>",
170
+ "<|sc|>",
171
+ "<|sr|>",
172
+ "<|sn|>",
173
+ "<|sd|>",
174
+ "<|si|>",
175
+ "<|sk|>",
176
+ "<|sl|>",
177
+ "<|so|>",
178
+ "<|st|>",
179
+ "<|es|>",
180
+ "<|su|>",
181
+ "<|sw|>",
182
+ "<|ss|>",
183
+ "<|sv|>",
184
+ "<|tl|>",
185
+ "<|ty|>",
186
+ "<|tg|>",
187
+ "<|ta|>",
188
+ "<|tt|>",
189
+ "<|te|>",
190
+ "<|th|>",
191
+ "<|bo|>",
192
+ "<|ti|>",
193
+ "<|to|>",
194
+ "<|ts|>",
195
+ "<|tn|>",
196
+ "<|tr|>",
197
+ "<|tk|>",
198
+ "<|tw|>",
199
+ "<|ug|>",
200
+ "<|uk|>",
201
+ "<|ur|>",
202
+ "<|uz|>",
203
+ "<|ve|>",
204
+ "<|vi|>",
205
+ "<|vo|>",
206
+ "<|wa|>",
207
+ "<|cy|>",
208
+ "<|wo|>",
209
+ "<|xh|>",
210
+ "<|ii|>",
211
+ "<|yi|>",
212
+ "<|yo|>",
213
+ "<|za|>",
214
+ "<|zu|>",
215
+ "<|spk0|>",
216
+ "<|spk1|>",
217
+ "<|spk2|>",
218
+ "<|spk3|>",
219
+ "<|spk4|>",
220
+ "<|spk5|>",
221
+ "<|spk6|>",
222
+ "<|spk7|>",
223
+ "<|spk8|>",
224
+ "<|spk9|>",
225
+ "<|spk10|>",
226
+ "<|spk11|>",
227
+ "<|spk12|>",
228
+ "<|spk13|>",
229
+ "<|spk14|>",
230
+ "<|spk15|>",
231
+ "<|spltoken0|>",
232
+ "<|spltoken1|>",
233
+ "<|spltoken2|>",
234
+ "<|spltoken3|>",
235
+ "<|spltoken4|>",
236
+ "<|spltoken5|>",
237
+ "<|spltoken6|>",
238
+ "<|spltoken7|>",
239
+ "<|spltoken8|>",
240
+ "<|spltoken9|>",
241
+ "<|spltoken10|>",
242
+ "<|spltoken11|>",
243
+ "<|spltoken12|>",
244
+ "<|spltoken13|>",
245
+ "<|spltoken14|>",
246
+ "<|spltoken15|>",
247
+ "<|spltoken16|>",
248
+ "<|spltoken17|>",
249
+ "<|spltoken18|>",
250
+ "<|spltoken19|>",
251
+ "<|spltoken20|>",
252
+ "<|spltoken21|>",
253
+ "<|spltoken22|>",
254
+ "<|spltoken23|>",
255
+ "<|spltoken24|>",
256
+ "<|spltoken25|>",
257
+ "<|spltoken26|>",
258
+ "<|spltoken27|>",
259
+ "<|spltoken28|>",
260
+ "<|spltoken29|>",
261
+ "<|spltoken30|>",
262
+ "<|spltoken31|>",
263
+ "<|spltoken32|>",
264
+ "<|spltoken33|>"
265
+ ],
266
+ "is_local": false,
267
+ "local_files_only": false,
268
+ "model_max_length": 2048,
269
+ "pad_token": "<pad>",
270
+ "processor_class": "CohereAsrProcessor",
271
+ "sp_model_kwargs": {},
272
+ "split_special_tokens": true,
273
+ "tokenizer_class": "TokenizersBackend",
274
+ "unk_token": "<unk>"
275
+ }