bzikst commited on
Commit
4ee837e
1 Parent(s): b2edc10

Initial commit

Browse files
Files changed (6) hide show
  1. README.md +11 -0
  2. config.json +240 -0
  3. model.bin +3 -0
  4. preprocessor_config.json +14 -0
  5. tokenizer.json +0 -0
  6. vocabulary.json +0 -0
README.md CHANGED
@@ -1,3 +1,14 @@
1
  ---
2
  license: apache-2.0
 
 
 
 
3
  ---
 
 
 
 
 
 
 
 
1
  ---
2
  license: apache-2.0
3
+ datasets:
4
+ - mozilla-foundation/common_voice_17_0
5
+ language:
6
+ - ru
7
  ---
8
+
9
+ This is ctranslate2 converted version of antony66/whisper-large-v3-russian
10
+
11
+ Command used to convert is
12
+ ```
13
+ ct2-transformers-converter --model antony66/whisper-large-v3-russian --output_dir faster-whisper-large-v3-ru-podlodka --copy_files tokenizer.json preprocessor_confi
14
+ g.json --quantization float16
config.json ADDED
@@ -0,0 +1,240 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alignment_heads": [
3
+ [
4
+ 7,
5
+ 0
6
+ ],
7
+ [
8
+ 10,
9
+ 17
10
+ ],
11
+ [
12
+ 12,
13
+ 18
14
+ ],
15
+ [
16
+ 13,
17
+ 12
18
+ ],
19
+ [
20
+ 16,
21
+ 1
22
+ ],
23
+ [
24
+ 17,
25
+ 14
26
+ ],
27
+ [
28
+ 19,
29
+ 11
30
+ ],
31
+ [
32
+ 21,
33
+ 4
34
+ ],
35
+ [
36
+ 24,
37
+ 1
38
+ ],
39
+ [
40
+ 25,
41
+ 6
42
+ ]
43
+ ],
44
+ "lang_ids": [
45
+ 50259,
46
+ 50260,
47
+ 50261,
48
+ 50262,
49
+ 50263,
50
+ 50264,
51
+ 50265,
52
+ 50266,
53
+ 50267,
54
+ 50268,
55
+ 50269,
56
+ 50270,
57
+ 50271,
58
+ 50272,
59
+ 50273,
60
+ 50274,
61
+ 50275,
62
+ 50276,
63
+ 50277,
64
+ 50278,
65
+ 50279,
66
+ 50280,
67
+ 50281,
68
+ 50282,
69
+ 50283,
70
+ 50284,
71
+ 50285,
72
+ 50286,
73
+ 50287,
74
+ 50288,
75
+ 50289,
76
+ 50290,
77
+ 50291,
78
+ 50292,
79
+ 50293,
80
+ 50294,
81
+ 50295,
82
+ 50296,
83
+ 50297,
84
+ 50298,
85
+ 50299,
86
+ 50300,
87
+ 50301,
88
+ 50302,
89
+ 50303,
90
+ 50304,
91
+ 50305,
92
+ 50306,
93
+ 50307,
94
+ 50308,
95
+ 50309,
96
+ 50310,
97
+ 50311,
98
+ 50312,
99
+ 50313,
100
+ 50314,
101
+ 50315,
102
+ 50316,
103
+ 50317,
104
+ 50318,
105
+ 50319,
106
+ 50320,
107
+ 50321,
108
+ 50322,
109
+ 50323,
110
+ 50324,
111
+ 50325,
112
+ 50326,
113
+ 50327,
114
+ 50328,
115
+ 50329,
116
+ 50330,
117
+ 50331,
118
+ 50332,
119
+ 50333,
120
+ 50334,
121
+ 50335,
122
+ 50336,
123
+ 50337,
124
+ 50338,
125
+ 50339,
126
+ 50340,
127
+ 50341,
128
+ 50342,
129
+ 50343,
130
+ 50344,
131
+ 50345,
132
+ 50346,
133
+ 50347,
134
+ 50348,
135
+ 50349,
136
+ 50350,
137
+ 50351,
138
+ 50352,
139
+ 50353,
140
+ 50354,
141
+ 50355,
142
+ 50356,
143
+ 50357,
144
+ 50358
145
+ ],
146
+ "suppress_ids": [
147
+ 1,
148
+ 2,
149
+ 7,
150
+ 8,
151
+ 9,
152
+ 10,
153
+ 14,
154
+ 25,
155
+ 26,
156
+ 27,
157
+ 28,
158
+ 29,
159
+ 31,
160
+ 58,
161
+ 59,
162
+ 60,
163
+ 61,
164
+ 62,
165
+ 63,
166
+ 90,
167
+ 91,
168
+ 92,
169
+ 93,
170
+ 359,
171
+ 503,
172
+ 522,
173
+ 542,
174
+ 873,
175
+ 893,
176
+ 902,
177
+ 918,
178
+ 922,
179
+ 931,
180
+ 1350,
181
+ 1853,
182
+ 1982,
183
+ 2460,
184
+ 2627,
185
+ 3246,
186
+ 3253,
187
+ 3268,
188
+ 3536,
189
+ 3846,
190
+ 3961,
191
+ 4183,
192
+ 4667,
193
+ 6585,
194
+ 6647,
195
+ 7273,
196
+ 9061,
197
+ 9383,
198
+ 10428,
199
+ 10929,
200
+ 11938,
201
+ 12033,
202
+ 12331,
203
+ 12562,
204
+ 13793,
205
+ 14157,
206
+ 14635,
207
+ 15265,
208
+ 15618,
209
+ 16553,
210
+ 16604,
211
+ 18362,
212
+ 18956,
213
+ 20075,
214
+ 21675,
215
+ 22520,
216
+ 26130,
217
+ 26161,
218
+ 26435,
219
+ 28279,
220
+ 29464,
221
+ 31650,
222
+ 32302,
223
+ 32470,
224
+ 36865,
225
+ 42863,
226
+ 47425,
227
+ 49870,
228
+ 50254,
229
+ 50258,
230
+ 50359,
231
+ 50360,
232
+ 50361,
233
+ 50362,
234
+ 50363
235
+ ],
236
+ "suppress_ids_begin": [
237
+ 220,
238
+ 50257
239
+ ]
240
+ }
model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3e8db916c498e9820303a2088bb2034a7413eb75f29b81699366a6d582d08aed
3
+ size 3087284276
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