Mimmiiz commited on
Commit
ea7464b
·
1 Parent(s): f208ac6

Upload WhisperForConditionalGeneration

Browse files
Files changed (3) hide show
  1. config.json +7 -7
  2. generation_config.json +119 -191
  3. model.safetensors +2 -2
config.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "_name_or_path": "openai/whisper-small",
3
  "activation_dropout": 0.0,
4
  "activation_function": "gelu",
5
  "apply_spec_augment": false,
@@ -9,7 +9,7 @@
9
  "attention_dropout": 0.0,
10
  "begin_suppress_tokens": [
11
  220,
12
- 50257
13
  ],
14
  "bos_token_id": 50257,
15
  "classifier_proj_size": 256,
@@ -18,13 +18,13 @@
18
  "decoder_ffn_dim": 3072,
19
  "decoder_layerdrop": 0.0,
20
  "decoder_layers": 12,
21
- "decoder_start_token_id": 50258,
22
  "dropout": 0.0,
23
  "encoder_attention_heads": 12,
24
  "encoder_ffn_dim": 3072,
25
  "encoder_layerdrop": 0.0,
26
  "encoder_layers": 12,
27
- "eos_token_id": 50257,
28
  "forced_decoder_ids": null,
29
  "init_std": 0.02,
30
  "is_encoder_decoder": true,
@@ -41,12 +41,12 @@
41
  "model_type": "whisper",
42
  "num_hidden_layers": 12,
43
  "num_mel_bins": 80,
44
- "pad_token_id": 50257,
45
  "scale_embedding": false,
46
  "suppress_tokens": [],
47
  "torch_dtype": "float32",
48
- "transformers_version": "4.36.0.dev0",
49
  "use_cache": false,
50
  "use_weighted_layer_sum": false,
51
- "vocab_size": 51865
52
  }
 
1
  {
2
+ "_name_or_path": "openai/whisper-small.en",
3
  "activation_dropout": 0.0,
4
  "activation_function": "gelu",
5
  "apply_spec_augment": false,
 
9
  "attention_dropout": 0.0,
10
  "begin_suppress_tokens": [
11
  220,
12
+ 50256
13
  ],
14
  "bos_token_id": 50257,
15
  "classifier_proj_size": 256,
 
18
  "decoder_ffn_dim": 3072,
19
  "decoder_layerdrop": 0.0,
20
  "decoder_layers": 12,
21
+ "decoder_start_token_id": 50257,
22
  "dropout": 0.0,
23
  "encoder_attention_heads": 12,
24
  "encoder_ffn_dim": 3072,
25
  "encoder_layerdrop": 0.0,
26
  "encoder_layers": 12,
27
+ "eos_token_id": 50256,
28
  "forced_decoder_ids": null,
29
  "init_std": 0.02,
30
  "is_encoder_decoder": true,
 
41
  "model_type": "whisper",
42
  "num_hidden_layers": 12,
43
  "num_mel_bins": 80,
44
+ "pad_token_id": 50256,
45
  "scale_embedding": false,
46
  "suppress_tokens": [],
47
  "torch_dtype": "float32",
48
+ "transformers_version": "4.37.0.dev0",
49
  "use_cache": false,
50
  "use_weighted_layer_sum": false,
51
+ "vocab_size": 51864
52
  }
generation_config.json CHANGED
@@ -1,170 +1,100 @@
1
  {
2
  "alignment_heads": [
3
  [
4
- 5,
 
 
 
 
 
 
 
 
5
  3
6
  ],
7
  [
8
- 5,
9
- 9
10
  ],
11
  [
12
  8,
13
- 0
14
  ],
15
  [
16
  8,
17
- 4
18
  ],
19
  [
20
  8,
21
  7
22
  ],
23
  [
24
- 8,
25
- 8
26
  ],
27
  [
28
  9,
29
- 0
30
  ],
31
  [
32
  9,
33
- 7
34
  ],
35
  [
36
  9,
37
- 9
38
  ],
39
  [
40
  10,
41
- 5
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
42
  ]
43
  ],
44
  "begin_suppress_tokens": [
45
  220,
46
- 50257
47
  ],
48
  "bos_token_id": 50257,
49
- "decoder_start_token_id": 50258,
50
- "eos_token_id": 50257,
51
  "forced_decoder_ids": [
52
  [
53
  1,
54
- null
55
- ],
56
- [
57
- 2,
58
- 50359
59
  ]
60
  ],
61
- "is_multilingual": true,
62
- "lang_to_id": {
63
- "<|af|>": 50327,
64
- "<|am|>": 50334,
65
- "<|ar|>": 50272,
66
- "<|as|>": 50350,
67
- "<|az|>": 50304,
68
- "<|ba|>": 50355,
69
- "<|be|>": 50330,
70
- "<|bg|>": 50292,
71
- "<|bn|>": 50302,
72
- "<|bo|>": 50347,
73
- "<|br|>": 50309,
74
- "<|bs|>": 50315,
75
- "<|ca|>": 50270,
76
- "<|cs|>": 50283,
77
- "<|cy|>": 50297,
78
- "<|da|>": 50285,
79
- "<|de|>": 50261,
80
- "<|el|>": 50281,
81
- "<|en|>": 50259,
82
- "<|es|>": 50262,
83
- "<|et|>": 50307,
84
- "<|eu|>": 50310,
85
- "<|fa|>": 50300,
86
- "<|fi|>": 50277,
87
- "<|fo|>": 50338,
88
- "<|fr|>": 50265,
89
- "<|gl|>": 50319,
90
- "<|gu|>": 50333,
91
- "<|haw|>": 50352,
92
- "<|ha|>": 50354,
93
- "<|he|>": 50279,
94
- "<|hi|>": 50276,
95
- "<|hr|>": 50291,
96
- "<|ht|>": 50339,
97
- "<|hu|>": 50286,
98
- "<|hy|>": 50312,
99
- "<|id|>": 50275,
100
- "<|is|>": 50311,
101
- "<|it|>": 50274,
102
- "<|ja|>": 50266,
103
- "<|jw|>": 50356,
104
- "<|ka|>": 50329,
105
- "<|kk|>": 50316,
106
- "<|km|>": 50323,
107
- "<|kn|>": 50306,
108
- "<|ko|>": 50264,
109
- "<|la|>": 50294,
110
- "<|lb|>": 50345,
111
- "<|ln|>": 50353,
112
- "<|lo|>": 50336,
113
- "<|lt|>": 50293,
114
- "<|lv|>": 50301,
115
- "<|mg|>": 50349,
116
- "<|mi|>": 50295,
117
- "<|mk|>": 50308,
118
- "<|ml|>": 50296,
119
- "<|mn|>": 50314,
120
- "<|mr|>": 50320,
121
- "<|ms|>": 50282,
122
- "<|mt|>": 50343,
123
- "<|my|>": 50346,
124
- "<|ne|>": 50313,
125
- "<|nl|>": 50271,
126
- "<|nn|>": 50342,
127
- "<|no|>": 50288,
128
- "<|oc|>": 50328,
129
- "<|pa|>": 50321,
130
- "<|pl|>": 50269,
131
- "<|ps|>": 50340,
132
- "<|pt|>": 50267,
133
- "<|ro|>": 50284,
134
- "<|ru|>": 50263,
135
- "<|sa|>": 50344,
136
- "<|sd|>": 50332,
137
- "<|si|>": 50322,
138
- "<|sk|>": 50298,
139
- "<|sl|>": 50305,
140
- "<|sn|>": 50324,
141
- "<|so|>": 50326,
142
- "<|sq|>": 50317,
143
- "<|sr|>": 50303,
144
- "<|su|>": 50357,
145
- "<|sv|>": 50273,
146
- "<|sw|>": 50318,
147
- "<|ta|>": 50287,
148
- "<|te|>": 50299,
149
- "<|tg|>": 50331,
150
- "<|th|>": 50289,
151
- "<|tk|>": 50341,
152
- "<|tl|>": 50348,
153
- "<|tr|>": 50268,
154
- "<|tt|>": 50351,
155
- "<|uk|>": 50280,
156
- "<|ur|>": 50290,
157
- "<|uz|>": 50337,
158
- "<|vi|>": 50278,
159
- "<|yi|>": 50335,
160
- "<|yo|>": 50325,
161
- "<|zh|>": 50260
162
- },
163
  "max_initial_timestamp_index": 1,
164
  "max_length": 448,
165
- "no_timestamps_token_id": 50363,
166
- "pad_token_id": 50257,
167
- "return_timestamps": false,
168
  "suppress_tokens": [
169
  1,
170
  2,
@@ -189,75 +119,73 @@
189
  91,
190
  92,
191
  93,
192
- 359,
193
- 503,
194
- 522,
195
- 542,
196
- 873,
197
- 893,
198
- 902,
199
- 918,
200
- 922,
201
- 931,
202
- 1350,
203
- 1853,
204
- 1982,
205
- 2460,
206
- 2627,
207
- 3246,
208
- 3253,
209
- 3268,
210
- 3536,
211
- 3846,
212
- 3961,
213
- 4183,
214
- 4667,
215
- 6585,
216
- 6647,
217
- 7273,
218
- 9061,
219
- 9383,
220
- 10428,
221
- 10929,
222
- 11938,
223
- 12033,
224
- 12331,
225
- 12562,
226
- 13793,
227
- 14157,
228
- 14635,
229
- 15265,
230
- 15618,
231
- 16553,
232
- 16604,
233
- 18362,
234
- 18956,
235
- 20075,
236
- 21675,
237
- 22520,
238
- 26130,
239
- 26161,
240
- 26435,
241
- 28279,
242
- 29464,
243
- 31650,
244
- 32302,
245
- 32470,
246
- 36865,
247
- 42863,
248
- 47425,
249
- 49870,
250
- 50254,
251
- 50258,
 
 
 
252
  50358,
253
  50359,
254
  50360,
255
- 50361,
256
- 50362
257
  ],
258
- "task_to_id": {
259
- "transcribe": 50359,
260
- "translate": 50358
261
- },
262
- "transformers_version": "4.36.0.dev0"
263
  }
 
1
  {
2
  "alignment_heads": [
3
  [
4
+ 6,
5
+ 6
6
+ ],
7
+ [
8
+ 7,
9
+ 0
10
+ ],
11
+ [
12
+ 7,
13
  3
14
  ],
15
  [
16
+ 7,
17
+ 8
18
  ],
19
  [
20
  8,
21
+ 2
22
  ],
23
  [
24
  8,
25
+ 5
26
  ],
27
  [
28
  8,
29
  7
30
  ],
31
  [
32
+ 9,
33
+ 0
34
  ],
35
  [
36
  9,
37
+ 4
38
  ],
39
  [
40
  9,
41
+ 8
42
  ],
43
  [
44
  9,
45
+ 10
46
  ],
47
  [
48
  10,
49
+ 0
50
+ ],
51
+ [
52
+ 10,
53
+ 1
54
+ ],
55
+ [
56
+ 10,
57
+ 2
58
+ ],
59
+ [
60
+ 10,
61
+ 3
62
+ ],
63
+ [
64
+ 10,
65
+ 6
66
+ ],
67
+ [
68
+ 10,
69
+ 11
70
+ ],
71
+ [
72
+ 11,
73
+ 2
74
+ ],
75
+ [
76
+ 11,
77
+ 4
78
  ]
79
  ],
80
  "begin_suppress_tokens": [
81
  220,
82
+ 50256
83
  ],
84
  "bos_token_id": 50257,
85
+ "decoder_start_token_id": 50257,
86
+ "eos_token_id": 50256,
87
  "forced_decoder_ids": [
88
  [
89
  1,
90
+ 50362
 
 
 
 
91
  ]
92
  ],
93
+ "is_multilingual": false,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
94
  "max_initial_timestamp_index": 1,
95
  "max_length": 448,
96
+ "no_timestamps_token_id": 50362,
97
+ "pad_token_id": 50256,
 
98
  "suppress_tokens": [
99
  1,
100
  2,
 
119
  91,
120
  92,
121
  93,
122
+ 357,
123
+ 366,
124
+ 438,
125
+ 532,
126
+ 685,
127
+ 705,
128
+ 796,
129
+ 930,
130
+ 1058,
131
+ 1220,
132
+ 1267,
133
+ 1279,
134
+ 1303,
135
+ 1343,
136
+ 1377,
137
+ 1391,
138
+ 1635,
139
+ 1782,
140
+ 1875,
141
+ 2162,
142
+ 2361,
143
+ 2488,
144
+ 3467,
145
+ 4008,
146
+ 4211,
147
+ 4600,
148
+ 4808,
149
+ 5299,
150
+ 5855,
151
+ 6329,
152
+ 7203,
153
+ 9609,
154
+ 9959,
155
+ 10563,
156
+ 10786,
157
+ 11420,
158
+ 11709,
159
+ 11907,
160
+ 13163,
161
+ 13697,
162
+ 13700,
163
+ 14808,
164
+ 15306,
165
+ 16410,
166
+ 16791,
167
+ 17992,
168
+ 19203,
169
+ 19510,
170
+ 20724,
171
+ 22305,
172
+ 22935,
173
+ 27007,
174
+ 30109,
175
+ 30420,
176
+ 33409,
177
+ 34949,
178
+ 40283,
179
+ 40493,
180
+ 40549,
181
+ 47282,
182
+ 49146,
183
+ 50257,
184
+ 50357,
185
  50358,
186
  50359,
187
  50360,
188
+ 50361
 
189
  ],
190
+ "transformers_version": "4.37.0.dev0"
 
 
 
 
191
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6cd92efd19ccde96900f6a5147ec797486a91337b15c7521f30915cc74e744b6
3
- size 966995080
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e26002565dd3d190bb4d986e83501a9761279a2307b9828dc0d020e7e44d0db7
3
+ size 966992008