arminhaberl commited on
Commit
5065f1e
1 Parent(s): b4adbe0
Files changed (6) hide show
  1. README.md +137 -0
  2. config.json +235 -0
  3. gitattributes.txt +34 -0
  4. model.bin +3 -0
  5. tokenizer.json +0 -0
  6. vocabulary.txt +0 -0
README.md CHANGED
@@ -1,3 +1,140 @@
1
  ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
2
  license: mit
 
3
  ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ tags:
103
+ - audio
104
+ - automatic-speech-recognition
105
  license: mit
106
+ library_name: ctranslate2
107
  ---
108
+
109
+ # Whisper large-v1 model for CTranslate2
110
+
111
+ This repository contains the conversion of [openai/whisper-large](https://huggingface.co/openai/whisper-large) to the [CTranslate2](https://github.com/OpenNMT/CTranslate2) model format.
112
+
113
+ This model can be used in CTranslate2 or projects based on CTranslate2 such as [faster-whisper](https://github.com/guillaumekln/faster-whisper).
114
+
115
+ ## Example
116
+
117
+ ```python
118
+ from faster_whisper import WhisperModel
119
+
120
+ model = WhisperModel("large-v1")
121
+
122
+ segments, info = model.transcribe("audio.mp3")
123
+ for segment in segments:
124
+ print("[%.2fs -> %.2fs] %s" % (segment.start, segment.end, segment.text))
125
+ ```
126
+
127
+ ## Conversion details
128
+
129
+ The original model was converted with the following command:
130
+
131
+ ```
132
+ ct2-transformers-converter --model openai/whisper-large --output_dir faster-whisper-large-v1 \
133
+ --copy_files tokenizer.json --quantization float16
134
+ ```
135
+
136
+ 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).
137
+
138
+ ## More information
139
+
140
+ **For more information about the original model, see its [model card](https://huggingface.co/openai/whisper-large).**
config.json ADDED
@@ -0,0 +1,235 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alignment_heads": [
3
+ [
4
+ 9,
5
+ 19
6
+ ],
7
+ [
8
+ 11,
9
+ 2
10
+ ],
11
+ [
12
+ 11,
13
+ 4
14
+ ],
15
+ [
16
+ 11,
17
+ 17
18
+ ],
19
+ [
20
+ 22,
21
+ 7
22
+ ],
23
+ [
24
+ 22,
25
+ 11
26
+ ],
27
+ [
28
+ 22,
29
+ 17
30
+ ],
31
+ [
32
+ 23,
33
+ 2
34
+ ],
35
+ [
36
+ 23,
37
+ 15
38
+ ]
39
+ ],
40
+ "lang_ids": [
41
+ 50259,
42
+ 50260,
43
+ 50261,
44
+ 50262,
45
+ 50263,
46
+ 50264,
47
+ 50265,
48
+ 50266,
49
+ 50267,
50
+ 50268,
51
+ 50269,
52
+ 50270,
53
+ 50271,
54
+ 50272,
55
+ 50273,
56
+ 50274,
57
+ 50275,
58
+ 50276,
59
+ 50277,
60
+ 50278,
61
+ 50279,
62
+ 50280,
63
+ 50281,
64
+ 50282,
65
+ 50283,
66
+ 50284,
67
+ 50285,
68
+ 50286,
69
+ 50287,
70
+ 50288,
71
+ 50289,
72
+ 50290,
73
+ 50291,
74
+ 50292,
75
+ 50293,
76
+ 50294,
77
+ 50295,
78
+ 50296,
79
+ 50297,
80
+ 50298,
81
+ 50299,
82
+ 50300,
83
+ 50301,
84
+ 50302,
85
+ 50303,
86
+ 50304,
87
+ 50305,
88
+ 50306,
89
+ 50307,
90
+ 50308,
91
+ 50309,
92
+ 50310,
93
+ 50311,
94
+ 50312,
95
+ 50313,
96
+ 50314,
97
+ 50315,
98
+ 50316,
99
+ 50317,
100
+ 50318,
101
+ 50319,
102
+ 50320,
103
+ 50321,
104
+ 50322,
105
+ 50323,
106
+ 50324,
107
+ 50325,
108
+ 50326,
109
+ 50327,
110
+ 50328,
111
+ 50329,
112
+ 50330,
113
+ 50331,
114
+ 50332,
115
+ 50333,
116
+ 50334,
117
+ 50335,
118
+ 50336,
119
+ 50337,
120
+ 50338,
121
+ 50339,
122
+ 50340,
123
+ 50341,
124
+ 50342,
125
+ 50343,
126
+ 50344,
127
+ 50345,
128
+ 50346,
129
+ 50347,
130
+ 50348,
131
+ 50349,
132
+ 50350,
133
+ 50351,
134
+ 50352,
135
+ 50353,
136
+ 50354,
137
+ 50355,
138
+ 50356,
139
+ 50357
140
+ ],
141
+ "suppress_ids": [
142
+ 1,
143
+ 2,
144
+ 7,
145
+ 8,
146
+ 9,
147
+ 10,
148
+ 14,
149
+ 25,
150
+ 26,
151
+ 27,
152
+ 28,
153
+ 29,
154
+ 31,
155
+ 58,
156
+ 59,
157
+ 60,
158
+ 61,
159
+ 62,
160
+ 63,
161
+ 90,
162
+ 91,
163
+ 92,
164
+ 93,
165
+ 359,
166
+ 503,
167
+ 522,
168
+ 542,
169
+ 873,
170
+ 893,
171
+ 902,
172
+ 918,
173
+ 922,
174
+ 931,
175
+ 1350,
176
+ 1853,
177
+ 1982,
178
+ 2460,
179
+ 2627,
180
+ 3246,
181
+ 3253,
182
+ 3268,
183
+ 3536,
184
+ 3846,
185
+ 3961,
186
+ 4183,
187
+ 4667,
188
+ 6585,
189
+ 6647,
190
+ 7273,
191
+ 9061,
192
+ 9383,
193
+ 10428,
194
+ 10929,
195
+ 11938,
196
+ 12033,
197
+ 12331,
198
+ 12562,
199
+ 13793,
200
+ 14157,
201
+ 14635,
202
+ 15265,
203
+ 15618,
204
+ 16553,
205
+ 16604,
206
+ 18362,
207
+ 18956,
208
+ 20075,
209
+ 21675,
210
+ 22520,
211
+ 26130,
212
+ 26161,
213
+ 26435,
214
+ 28279,
215
+ 29464,
216
+ 31650,
217
+ 32302,
218
+ 32470,
219
+ 36865,
220
+ 42863,
221
+ 47425,
222
+ 49870,
223
+ 50254,
224
+ 50258,
225
+ 50358,
226
+ 50359,
227
+ 50360,
228
+ 50361,
229
+ 50362
230
+ ],
231
+ "suppress_ids_begin": [
232
+ 220,
233
+ 50257
234
+ ]
235
+ }
gitattributes.txt ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ *.tflite filter=lfs diff=lfs merge=lfs -text
29
+ *.tgz filter=lfs diff=lfs merge=lfs -text
30
+ *.wasm filter=lfs diff=lfs merge=lfs -text
31
+ *.xz filter=lfs diff=lfs merge=lfs -text
32
+ *.zip filter=lfs diff=lfs merge=lfs -text
33
+ *.zst filter=lfs diff=lfs merge=lfs -text
34
+ *tfevents* filter=lfs diff=lfs merge=lfs -text
model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a3cce8081a5414206ab09a80aa410ebf9965feef52adafeead13f4a83398b1d1
3
+ size 3086912962
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
vocabulary.txt ADDED
The diff for this file is too large to render. See raw diff