arminhaberl deepdml commited on
Commit
df99141
·
verified ·
0 Parent(s):

Duplicate from deepdml/faster-whisper-large-v3-turbo-ct2

Browse files

Co-authored-by: D <[email protected]>

Files changed (7) hide show
  1. .gitattributes +35 -0
  2. README.md +141 -0
  3. config.json +360 -0
  4. model.bin +3 -0
  5. preprocessor_config.json +14 -0
  6. tokenizer.json +0 -0
  7. vocabulary.json +0 -0
.gitattributes ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ *.7z filter=lfs diff=lfs merge=lfs -text
2
+ *.arrow filter=lfs diff=lfs merge=lfs -text
3
+ *.bin filter=lfs diff=lfs merge=lfs -text
4
+ *.bz2 filter=lfs diff=lfs merge=lfs -text
5
+ *.ckpt filter=lfs diff=lfs merge=lfs -text
6
+ *.ftz filter=lfs diff=lfs merge=lfs -text
7
+ *.gz filter=lfs diff=lfs merge=lfs -text
8
+ *.h5 filter=lfs diff=lfs merge=lfs -text
9
+ *.joblib filter=lfs diff=lfs merge=lfs -text
10
+ *.lfs.* filter=lfs diff=lfs merge=lfs -text
11
+ *.mlmodel filter=lfs diff=lfs merge=lfs -text
12
+ *.model filter=lfs diff=lfs merge=lfs -text
13
+ *.msgpack filter=lfs diff=lfs merge=lfs -text
14
+ *.npy filter=lfs diff=lfs merge=lfs -text
15
+ *.npz filter=lfs diff=lfs merge=lfs -text
16
+ *.onnx filter=lfs diff=lfs merge=lfs -text
17
+ *.ot filter=lfs diff=lfs merge=lfs -text
18
+ *.parquet filter=lfs diff=lfs merge=lfs -text
19
+ *.pb filter=lfs diff=lfs merge=lfs -text
20
+ *.pickle filter=lfs diff=lfs merge=lfs -text
21
+ *.pkl filter=lfs diff=lfs merge=lfs -text
22
+ *.pt filter=lfs diff=lfs merge=lfs -text
23
+ *.pth filter=lfs diff=lfs merge=lfs -text
24
+ *.rar filter=lfs diff=lfs merge=lfs -text
25
+ *.safetensors filter=lfs diff=lfs merge=lfs -text
26
+ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
27
+ *.tar.* filter=lfs diff=lfs merge=lfs -text
28
+ *.tar filter=lfs diff=lfs merge=lfs -text
29
+ *.tflite filter=lfs diff=lfs merge=lfs -text
30
+ *.tgz filter=lfs diff=lfs merge=lfs -text
31
+ *.wasm filter=lfs diff=lfs merge=lfs -text
32
+ *.xz filter=lfs diff=lfs merge=lfs -text
33
+ *.zip filter=lfs diff=lfs merge=lfs -text
34
+ *.zst filter=lfs diff=lfs merge=lfs -text
35
+ *tfevents* filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,141 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language:
3
+ - en
4
+ - zh
5
+ - de
6
+ - es
7
+ - ru
8
+ - ko
9
+ - fr
10
+ - ja
11
+ - pt
12
+ - tr
13
+ - pl
14
+ - ca
15
+ - nl
16
+ - ar
17
+ - sv
18
+ - it
19
+ - id
20
+ - hi
21
+ - fi
22
+ - vi
23
+ - he
24
+ - uk
25
+ - el
26
+ - ms
27
+ - cs
28
+ - ro
29
+ - da
30
+ - hu
31
+ - ta
32
+ - 'no'
33
+ - th
34
+ - ur
35
+ - hr
36
+ - bg
37
+ - lt
38
+ - la
39
+ - mi
40
+ - ml
41
+ - cy
42
+ - sk
43
+ - te
44
+ - fa
45
+ - lv
46
+ - bn
47
+ - sr
48
+ - az
49
+ - sl
50
+ - kn
51
+ - et
52
+ - mk
53
+ - br
54
+ - eu
55
+ - is
56
+ - hy
57
+ - ne
58
+ - mn
59
+ - bs
60
+ - kk
61
+ - sq
62
+ - sw
63
+ - gl
64
+ - mr
65
+ - pa
66
+ - si
67
+ - km
68
+ - sn
69
+ - yo
70
+ - so
71
+ - af
72
+ - oc
73
+ - ka
74
+ - be
75
+ - tg
76
+ - sd
77
+ - gu
78
+ - am
79
+ - yi
80
+ - lo
81
+ - uz
82
+ - fo
83
+ - ht
84
+ - ps
85
+ - tk
86
+ - nn
87
+ - mt
88
+ - sa
89
+ - lb
90
+ - my
91
+ - bo
92
+ - tl
93
+ - mg
94
+ - as
95
+ - tt
96
+ - haw
97
+ - ln
98
+ - ha
99
+ - ba
100
+ - jw
101
+ - su
102
+ - yue
103
+ tags:
104
+ - audio
105
+ - automatic-speech-recognition
106
+ license: mit
107
+ library_name: ctranslate2
108
+ ---
109
+
110
+ # Whisper large-v3 model for CTranslate2
111
+
112
+ This repository contains the conversion of [deepdml/whisper-large-v3-turbo](https://huggingface.co/deepdml/whisper-large-v3-turbo) to the [CTranslate2](https://github.com/OpenNMT/CTranslate2) model format.
113
+
114
+ This model can be used in CTranslate2 or projects based on CTranslate2 such as [faster-whisper](https://github.com/systran/faster-whisper).
115
+
116
+ ## Example
117
+
118
+ ```python
119
+ from faster_whisper import WhisperModel
120
+
121
+ model = WhisperModel("faster-whisper-large-v3-turbo-ct2")
122
+
123
+ segments, info = model.transcribe("audio.mp3")
124
+ for segment in segments:
125
+ print("[%.2fs -> %.2fs] %s" % (segment.start, segment.end, segment.text))
126
+ ```
127
+
128
+ ## Conversion details
129
+
130
+ The original model was converted with the following command:
131
+
132
+ ```
133
+ ct2-transformers-converter --model deepdml/whisper-large-v3-turbo --output_dir faster-whisper-large-v3-turbo \
134
+ --copy_files tokenizer.json preprocessor_config.json --quantization float16
135
+ ```
136
+
137
+ Note that the model weights are saved in FP16. This type can be changed when the model is loaded using the [`compute_type` option in CTranslate2](https://opennmt.net/CTranslate2/quantization.html).
138
+
139
+ ## More information
140
+
141
+ **For more information about the original model, see its [model card](https://huggingface.co/openai/whisper-large-v3).**
config.json ADDED
@@ -0,0 +1,360 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alignment_heads": [
3
+ [
4
+ 2,
5
+ 0
6
+ ],
7
+ [
8
+ 2,
9
+ 1
10
+ ],
11
+ [
12
+ 2,
13
+ 2
14
+ ],
15
+ [
16
+ 2,
17
+ 3
18
+ ],
19
+ [
20
+ 2,
21
+ 4
22
+ ],
23
+ [
24
+ 2,
25
+ 5
26
+ ],
27
+ [
28
+ 2,
29
+ 6
30
+ ],
31
+ [
32
+ 2,
33
+ 7
34
+ ],
35
+ [
36
+ 2,
37
+ 8
38
+ ],
39
+ [
40
+ 2,
41
+ 9
42
+ ],
43
+ [
44
+ 2,
45
+ 10
46
+ ],
47
+ [
48
+ 2,
49
+ 11
50
+ ],
51
+ [
52
+ 2,
53
+ 12
54
+ ],
55
+ [
56
+ 2,
57
+ 13
58
+ ],
59
+ [
60
+ 2,
61
+ 14
62
+ ],
63
+ [
64
+ 2,
65
+ 15
66
+ ],
67
+ [
68
+ 2,
69
+ 16
70
+ ],
71
+ [
72
+ 2,
73
+ 17
74
+ ],
75
+ [
76
+ 2,
77
+ 18
78
+ ],
79
+ [
80
+ 2,
81
+ 19
82
+ ],
83
+ [
84
+ 3,
85
+ 0
86
+ ],
87
+ [
88
+ 3,
89
+ 1
90
+ ],
91
+ [
92
+ 3,
93
+ 2
94
+ ],
95
+ [
96
+ 3,
97
+ 3
98
+ ],
99
+ [
100
+ 3,
101
+ 4
102
+ ],
103
+ [
104
+ 3,
105
+ 5
106
+ ],
107
+ [
108
+ 3,
109
+ 6
110
+ ],
111
+ [
112
+ 3,
113
+ 7
114
+ ],
115
+ [
116
+ 3,
117
+ 8
118
+ ],
119
+ [
120
+ 3,
121
+ 9
122
+ ],
123
+ [
124
+ 3,
125
+ 10
126
+ ],
127
+ [
128
+ 3,
129
+ 11
130
+ ],
131
+ [
132
+ 3,
133
+ 12
134
+ ],
135
+ [
136
+ 3,
137
+ 13
138
+ ],
139
+ [
140
+ 3,
141
+ 14
142
+ ],
143
+ [
144
+ 3,
145
+ 15
146
+ ],
147
+ [
148
+ 3,
149
+ 16
150
+ ],
151
+ [
152
+ 3,
153
+ 17
154
+ ],
155
+ [
156
+ 3,
157
+ 18
158
+ ],
159
+ [
160
+ 3,
161
+ 19
162
+ ]
163
+ ],
164
+ "lang_ids": [
165
+ 50259,
166
+ 50260,
167
+ 50261,
168
+ 50262,
169
+ 50263,
170
+ 50264,
171
+ 50265,
172
+ 50266,
173
+ 50267,
174
+ 50268,
175
+ 50269,
176
+ 50270,
177
+ 50271,
178
+ 50272,
179
+ 50273,
180
+ 50274,
181
+ 50275,
182
+ 50276,
183
+ 50277,
184
+ 50278,
185
+ 50279,
186
+ 50280,
187
+ 50281,
188
+ 50282,
189
+ 50283,
190
+ 50284,
191
+ 50285,
192
+ 50286,
193
+ 50287,
194
+ 50288,
195
+ 50289,
196
+ 50290,
197
+ 50291,
198
+ 50292,
199
+ 50293,
200
+ 50294,
201
+ 50295,
202
+ 50296,
203
+ 50297,
204
+ 50298,
205
+ 50299,
206
+ 50300,
207
+ 50301,
208
+ 50302,
209
+ 50303,
210
+ 50304,
211
+ 50305,
212
+ 50306,
213
+ 50307,
214
+ 50308,
215
+ 50309,
216
+ 50310,
217
+ 50311,
218
+ 50312,
219
+ 50313,
220
+ 50314,
221
+ 50315,
222
+ 50316,
223
+ 50317,
224
+ 50318,
225
+ 50319,
226
+ 50320,
227
+ 50321,
228
+ 50322,
229
+ 50323,
230
+ 50324,
231
+ 50325,
232
+ 50326,
233
+ 50327,
234
+ 50328,
235
+ 50329,
236
+ 50330,
237
+ 50331,
238
+ 50332,
239
+ 50333,
240
+ 50334,
241
+ 50335,
242
+ 50336,
243
+ 50337,
244
+ 50338,
245
+ 50339,
246
+ 50340,
247
+ 50341,
248
+ 50342,
249
+ 50343,
250
+ 50344,
251
+ 50345,
252
+ 50346,
253
+ 50347,
254
+ 50348,
255
+ 50349,
256
+ 50350,
257
+ 50351,
258
+ 50352,
259
+ 50353,
260
+ 50354,
261
+ 50355,
262
+ 50356,
263
+ 50357,
264
+ 50358
265
+ ],
266
+ "suppress_ids": [
267
+ 1,
268
+ 2,
269
+ 7,
270
+ 8,
271
+ 9,
272
+ 10,
273
+ 14,
274
+ 25,
275
+ 26,
276
+ 27,
277
+ 28,
278
+ 29,
279
+ 31,
280
+ 58,
281
+ 59,
282
+ 60,
283
+ 61,
284
+ 62,
285
+ 63,
286
+ 90,
287
+ 91,
288
+ 92,
289
+ 93,
290
+ 359,
291
+ 503,
292
+ 522,
293
+ 542,
294
+ 873,
295
+ 893,
296
+ 902,
297
+ 918,
298
+ 922,
299
+ 931,
300
+ 1350,
301
+ 1853,
302
+ 1982,
303
+ 2460,
304
+ 2627,
305
+ 3246,
306
+ 3253,
307
+ 3268,
308
+ 3536,
309
+ 3846,
310
+ 3961,
311
+ 4183,
312
+ 4667,
313
+ 6585,
314
+ 6647,
315
+ 7273,
316
+ 9061,
317
+ 9383,
318
+ 10428,
319
+ 10929,
320
+ 11938,
321
+ 12033,
322
+ 12331,
323
+ 12562,
324
+ 13793,
325
+ 14157,
326
+ 14635,
327
+ 15265,
328
+ 15618,
329
+ 16553,
330
+ 16604,
331
+ 18362,
332
+ 18956,
333
+ 20075,
334
+ 21675,
335
+ 22520,
336
+ 26130,
337
+ 26161,
338
+ 26435,
339
+ 28279,
340
+ 29464,
341
+ 31650,
342
+ 32302,
343
+ 32470,
344
+ 36865,
345
+ 42863,
346
+ 47425,
347
+ 49870,
348
+ 50254,
349
+ 50258,
350
+ 50359,
351
+ 50360,
352
+ 50361,
353
+ 50362,
354
+ 50363
355
+ ],
356
+ "suppress_ids_begin": [
357
+ 220,
358
+ 50257
359
+ ]
360
+ }
model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e76620f83d5f5b69efd3d87e3dc180c1bd21df9fbebacfd4335e5e1efcc018da
3
+ size 1617884929
preprocessor_config.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "chunk_length": 30,
3
+ "feature_extractor_type": "WhisperFeatureExtractor",
4
+ "feature_size": 128,
5
+ "hop_length": 160,
6
+ "n_fft": 400,
7
+ "n_samples": 480000,
8
+ "nb_max_frames": 3000,
9
+ "padding_side": "right",
10
+ "padding_value": 0.0,
11
+ "processor_class": "WhisperProcessor",
12
+ "return_attention_mask": false,
13
+ "sampling_rate": 16000
14
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
vocabulary.json ADDED
The diff for this file is too large to render. See raw diff