Upload WhisperForConditionalGeneration

#1
by Mariszka - opened
Files changed (2) hide show
  1. config.json +12 -2
  2. generation_config.json +246 -0
config.json CHANGED
@@ -1,7 +1,8 @@
1
  {
2
- "_name_or_path": "openai/whisper-medium",
3
  "activation_dropout": 0.0,
4
  "activation_function": "gelu",
 
5
  "architectures": [
6
  "WhisperForConditionalGeneration"
7
  ],
@@ -11,6 +12,7 @@
11
  50257
12
  ],
13
  "bos_token_id": 50257,
 
14
  "d_model": 1024,
15
  "decoder_attention_heads": 16,
16
  "decoder_ffn_dim": 4096,
@@ -26,16 +28,24 @@
26
  "forced_decoder_ids": null,
27
  "init_std": 0.02,
28
  "is_encoder_decoder": true,
 
 
 
 
 
 
29
  "max_length": 448,
30
  "max_source_positions": 1500,
31
  "max_target_positions": 448,
 
32
  "model_type": "whisper",
33
  "num_hidden_layers": 24,
34
  "num_mel_bins": 80,
35
  "pad_token_id": 50257,
36
  "scale_embedding": false,
37
  "torch_dtype": "float32",
38
- "transformers_version": "4.26.0.dev0",
39
  "use_cache": true,
 
40
  "vocab_size": 51865
41
  }
 
1
  {
2
+ "_name_or_path": "Mariszka/whisper-medium-cs-cv11",
3
  "activation_dropout": 0.0,
4
  "activation_function": "gelu",
5
+ "apply_spec_augment": false,
6
  "architectures": [
7
  "WhisperForConditionalGeneration"
8
  ],
 
12
  50257
13
  ],
14
  "bos_token_id": 50257,
15
+ "classifier_proj_size": 256,
16
  "d_model": 1024,
17
  "decoder_attention_heads": 16,
18
  "decoder_ffn_dim": 4096,
 
28
  "forced_decoder_ids": null,
29
  "init_std": 0.02,
30
  "is_encoder_decoder": true,
31
+ "mask_feature_length": 10,
32
+ "mask_feature_min_masks": 0,
33
+ "mask_feature_prob": 0.0,
34
+ "mask_time_length": 10,
35
+ "mask_time_min_masks": 2,
36
+ "mask_time_prob": 0.05,
37
  "max_length": 448,
38
  "max_source_positions": 1500,
39
  "max_target_positions": 448,
40
+ "median_filter_width": 7,
41
  "model_type": "whisper",
42
  "num_hidden_layers": 24,
43
  "num_mel_bins": 80,
44
  "pad_token_id": 50257,
45
  "scale_embedding": false,
46
  "torch_dtype": "float32",
47
+ "transformers_version": "4.36.2",
48
  "use_cache": true,
49
+ "use_weighted_layer_sum": false,
50
  "vocab_size": 51865
51
  }
generation_config.json ADDED
@@ -0,0 +1,246 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alignment_heads": [
3
+ [
4
+ 13,
5
+ 15
6
+ ],
7
+ [
8
+ 15,
9
+ 4
10
+ ],
11
+ [
12
+ 15,
13
+ 15
14
+ ],
15
+ [
16
+ 16,
17
+ 1
18
+ ],
19
+ [
20
+ 20,
21
+ 0
22
+ ],
23
+ [
24
+ 23,
25
+ 4
26
+ ]
27
+ ],
28
+ "begin_suppress_tokens": [
29
+ 220,
30
+ 50257
31
+ ],
32
+ "bos_token_id": 50257,
33
+ "decoder_start_token_id": 50258,
34
+ "eos_token_id": 50257,
35
+ "forced_decoder_ids": [
36
+ [
37
+ 1,
38
+ null
39
+ ],
40
+ [
41
+ 2,
42
+ 50359
43
+ ]
44
+ ],
45
+ "is_multilingual": true,
46
+ "lang_to_id": {
47
+ "<|af|>": 50327,
48
+ "<|am|>": 50334,
49
+ "<|ar|>": 50272,
50
+ "<|as|>": 50350,
51
+ "<|az|>": 50304,
52
+ "<|ba|>": 50355,
53
+ "<|be|>": 50330,
54
+ "<|bg|>": 50292,
55
+ "<|bn|>": 50302,
56
+ "<|bo|>": 50347,
57
+ "<|br|>": 50309,
58
+ "<|bs|>": 50315,
59
+ "<|ca|>": 50270,
60
+ "<|cs|>": 50283,
61
+ "<|cy|>": 50297,
62
+ "<|da|>": 50285,
63
+ "<|de|>": 50261,
64
+ "<|el|>": 50281,
65
+ "<|en|>": 50259,
66
+ "<|es|>": 50262,
67
+ "<|et|>": 50307,
68
+ "<|eu|>": 50310,
69
+ "<|fa|>": 50300,
70
+ "<|fi|>": 50277,
71
+ "<|fo|>": 50338,
72
+ "<|fr|>": 50265,
73
+ "<|gl|>": 50319,
74
+ "<|gu|>": 50333,
75
+ "<|haw|>": 50352,
76
+ "<|ha|>": 50354,
77
+ "<|he|>": 50279,
78
+ "<|hi|>": 50276,
79
+ "<|hr|>": 50291,
80
+ "<|ht|>": 50339,
81
+ "<|hu|>": 50286,
82
+ "<|hy|>": 50312,
83
+ "<|id|>": 50275,
84
+ "<|is|>": 50311,
85
+ "<|it|>": 50274,
86
+ "<|ja|>": 50266,
87
+ "<|jw|>": 50356,
88
+ "<|ka|>": 50329,
89
+ "<|kk|>": 50316,
90
+ "<|km|>": 50323,
91
+ "<|kn|>": 50306,
92
+ "<|ko|>": 50264,
93
+ "<|la|>": 50294,
94
+ "<|lb|>": 50345,
95
+ "<|ln|>": 50353,
96
+ "<|lo|>": 50336,
97
+ "<|lt|>": 50293,
98
+ "<|lv|>": 50301,
99
+ "<|mg|>": 50349,
100
+ "<|mi|>": 50295,
101
+ "<|mk|>": 50308,
102
+ "<|ml|>": 50296,
103
+ "<|mn|>": 50314,
104
+ "<|mr|>": 50320,
105
+ "<|ms|>": 50282,
106
+ "<|mt|>": 50343,
107
+ "<|my|>": 50346,
108
+ "<|ne|>": 50313,
109
+ "<|nl|>": 50271,
110
+ "<|nn|>": 50342,
111
+ "<|no|>": 50288,
112
+ "<|oc|>": 50328,
113
+ "<|pa|>": 50321,
114
+ "<|pl|>": 50269,
115
+ "<|ps|>": 50340,
116
+ "<|pt|>": 50267,
117
+ "<|ro|>": 50284,
118
+ "<|ru|>": 50263,
119
+ "<|sa|>": 50344,
120
+ "<|sd|>": 50332,
121
+ "<|si|>": 50322,
122
+ "<|sk|>": 50298,
123
+ "<|sl|>": 50305,
124
+ "<|sn|>": 50324,
125
+ "<|so|>": 50326,
126
+ "<|sq|>": 50317,
127
+ "<|sr|>": 50303,
128
+ "<|su|>": 50357,
129
+ "<|sv|>": 50273,
130
+ "<|sw|>": 50318,
131
+ "<|ta|>": 50287,
132
+ "<|te|>": 50299,
133
+ "<|tg|>": 50331,
134
+ "<|th|>": 50289,
135
+ "<|tk|>": 50341,
136
+ "<|tl|>": 50348,
137
+ "<|tr|>": 50268,
138
+ "<|tt|>": 50351,
139
+ "<|uk|>": 50280,
140
+ "<|ur|>": 50290,
141
+ "<|uz|>": 50337,
142
+ "<|vi|>": 50278,
143
+ "<|yi|>": 50335,
144
+ "<|yo|>": 50325,
145
+ "<|zh|>": 50260
146
+ },
147
+ "max_initial_timestamp_index": 1,
148
+ "max_length": 448,
149
+ "no_timestamps_token_id": 50363,
150
+ "pad_token_id": 50257,
151
+ "suppress_tokens": [
152
+ 1,
153
+ 2,
154
+ 7,
155
+ 8,
156
+ 9,
157
+ 10,
158
+ 14,
159
+ 25,
160
+ 26,
161
+ 27,
162
+ 28,
163
+ 29,
164
+ 31,
165
+ 58,
166
+ 59,
167
+ 60,
168
+ 61,
169
+ 62,
170
+ 63,
171
+ 90,
172
+ 91,
173
+ 92,
174
+ 93,
175
+ 359,
176
+ 503,
177
+ 522,
178
+ 542,
179
+ 873,
180
+ 893,
181
+ 902,
182
+ 918,
183
+ 922,
184
+ 931,
185
+ 1350,
186
+ 1853,
187
+ 1982,
188
+ 2460,
189
+ 2627,
190
+ 3246,
191
+ 3253,
192
+ 3268,
193
+ 3536,
194
+ 3846,
195
+ 3961,
196
+ 4183,
197
+ 4667,
198
+ 6585,
199
+ 6647,
200
+ 7273,
201
+ 9061,
202
+ 9383,
203
+ 10428,
204
+ 10929,
205
+ 11938,
206
+ 12033,
207
+ 12331,
208
+ 12562,
209
+ 13793,
210
+ 14157,
211
+ 14635,
212
+ 15265,
213
+ 15618,
214
+ 16553,
215
+ 16604,
216
+ 18362,
217
+ 18956,
218
+ 20075,
219
+ 21675,
220
+ 22520,
221
+ 26130,
222
+ 26161,
223
+ 26435,
224
+ 28279,
225
+ 29464,
226
+ 31650,
227
+ 32302,
228
+ 32470,
229
+ 36865,
230
+ 42863,
231
+ 47425,
232
+ 49870,
233
+ 50254,
234
+ 50258,
235
+ 50358,
236
+ 50359,
237
+ 50360,
238
+ 50361,
239
+ 50362
240
+ ],
241
+ "task_to_id": {
242
+ "transcribe": 50359,
243
+ "translate": 50358
244
+ },
245
+ "transformers_version": "4.36.2"
246
+ }