Automatic Speech Recognition
Transformers
PyTorch
Thai
whisper
Inference Endpoints
tensorops commited on
Commit
72b7d82
1 Parent(s): 68ddaee

Upload WhisperForConditionalGeneration

Browse files
Files changed (3) hide show
  1. config.json +15 -2
  2. generation_config.json +220 -0
  3. pytorch_model.bin +2 -2
config.json CHANGED
@@ -4,7 +4,7 @@
4
  "activation_function": "gelu",
5
  "apply_spec_augment": true,
6
  "architectures": [
7
- "WhisperModel"
8
  ],
9
  "attention_dropout": 0.0,
10
  "begin_suppress_tokens": [
@@ -25,7 +25,20 @@
25
  "encoder_layerdrop": 0.0,
26
  "encoder_layers": 24,
27
  "eos_token_id": 50257,
28
- "forced_decoder_ids": null,
 
 
 
 
 
 
 
 
 
 
 
 
 
29
  "init_std": 0.02,
30
  "is_encoder_decoder": true,
31
  "mask_feature_length": 64,
 
4
  "activation_function": "gelu",
5
  "apply_spec_augment": true,
6
  "architectures": [
7
+ "WhisperForConditionalGeneration"
8
  ],
9
  "attention_dropout": 0.0,
10
  "begin_suppress_tokens": [
 
25
  "encoder_layerdrop": 0.0,
26
  "encoder_layers": 24,
27
  "eos_token_id": 50257,
28
+ "forced_decoder_ids": [
29
+ [
30
+ 1,
31
+ 50289
32
+ ],
33
+ [
34
+ 2,
35
+ 50359
36
+ ],
37
+ [
38
+ 3,
39
+ 50363
40
+ ]
41
+ ],
42
  "init_std": 0.02,
43
  "is_encoder_decoder": true,
44
  "mask_feature_length": 64,
generation_config.json ADDED
@@ -0,0 +1,220 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "begin_suppress_tokens": [
3
+ 220,
4
+ 50257
5
+ ],
6
+ "bos_token_id": 50257,
7
+ "decoder_start_token_id": 50258,
8
+ "eos_token_id": 50257,
9
+ "forced_decoder_ids": [
10
+ [
11
+ 1,
12
+ null
13
+ ],
14
+ [
15
+ 2,
16
+ 50359
17
+ ]
18
+ ],
19
+ "is_multilingual": true,
20
+ "lang_to_id": {
21
+ "<|af|>": 50327,
22
+ "<|am|>": 50334,
23
+ "<|ar|>": 50272,
24
+ "<|as|>": 50350,
25
+ "<|az|>": 50304,
26
+ "<|ba|>": 50355,
27
+ "<|be|>": 50330,
28
+ "<|bg|>": 50292,
29
+ "<|bn|>": 50302,
30
+ "<|bo|>": 50347,
31
+ "<|br|>": 50309,
32
+ "<|bs|>": 50315,
33
+ "<|ca|>": 50270,
34
+ "<|cs|>": 50283,
35
+ "<|cy|>": 50297,
36
+ "<|da|>": 50285,
37
+ "<|de|>": 50261,
38
+ "<|el|>": 50281,
39
+ "<|en|>": 50259,
40
+ "<|es|>": 50262,
41
+ "<|et|>": 50307,
42
+ "<|eu|>": 50310,
43
+ "<|fa|>": 50300,
44
+ "<|fi|>": 50277,
45
+ "<|fo|>": 50338,
46
+ "<|fr|>": 50265,
47
+ "<|gl|>": 50319,
48
+ "<|gu|>": 50333,
49
+ "<|haw|>": 50352,
50
+ "<|ha|>": 50354,
51
+ "<|he|>": 50279,
52
+ "<|hi|>": 50276,
53
+ "<|hr|>": 50291,
54
+ "<|ht|>": 50339,
55
+ "<|hu|>": 50286,
56
+ "<|hy|>": 50312,
57
+ "<|id|>": 50275,
58
+ "<|is|>": 50311,
59
+ "<|it|>": 50274,
60
+ "<|ja|>": 50266,
61
+ "<|jw|>": 50356,
62
+ "<|ka|>": 50329,
63
+ "<|kk|>": 50316,
64
+ "<|km|>": 50323,
65
+ "<|kn|>": 50306,
66
+ "<|ko|>": 50264,
67
+ "<|la|>": 50294,
68
+ "<|lb|>": 50345,
69
+ "<|ln|>": 50353,
70
+ "<|lo|>": 50336,
71
+ "<|lt|>": 50293,
72
+ "<|lv|>": 50301,
73
+ "<|mg|>": 50349,
74
+ "<|mi|>": 50295,
75
+ "<|mk|>": 50308,
76
+ "<|ml|>": 50296,
77
+ "<|mn|>": 50314,
78
+ "<|mr|>": 50320,
79
+ "<|ms|>": 50282,
80
+ "<|mt|>": 50343,
81
+ "<|my|>": 50346,
82
+ "<|ne|>": 50313,
83
+ "<|nl|>": 50271,
84
+ "<|nn|>": 50342,
85
+ "<|no|>": 50288,
86
+ "<|oc|>": 50328,
87
+ "<|pa|>": 50321,
88
+ "<|pl|>": 50269,
89
+ "<|ps|>": 50340,
90
+ "<|pt|>": 50267,
91
+ "<|ro|>": 50284,
92
+ "<|ru|>": 50263,
93
+ "<|sa|>": 50344,
94
+ "<|sd|>": 50332,
95
+ "<|si|>": 50322,
96
+ "<|sk|>": 50298,
97
+ "<|sl|>": 50305,
98
+ "<|sn|>": 50324,
99
+ "<|so|>": 50326,
100
+ "<|sq|>": 50317,
101
+ "<|sr|>": 50303,
102
+ "<|su|>": 50357,
103
+ "<|sv|>": 50273,
104
+ "<|sw|>": 50318,
105
+ "<|ta|>": 50287,
106
+ "<|te|>": 50299,
107
+ "<|tg|>": 50331,
108
+ "<|th|>": 50289,
109
+ "<|tk|>": 50341,
110
+ "<|tl|>": 50348,
111
+ "<|tr|>": 50268,
112
+ "<|tt|>": 50351,
113
+ "<|uk|>": 50280,
114
+ "<|ur|>": 50290,
115
+ "<|uz|>": 50337,
116
+ "<|vi|>": 50278,
117
+ "<|yi|>": 50335,
118
+ "<|yo|>": 50325,
119
+ "<|zh|>": 50260
120
+ },
121
+ "max_initial_timestamp_index": 1,
122
+ "max_length": 448,
123
+ "no_timestamps_token_id": 50363,
124
+ "pad_token_id": 50257,
125
+ "suppress_tokens": [
126
+ 1,
127
+ 2,
128
+ 7,
129
+ 8,
130
+ 9,
131
+ 10,
132
+ 14,
133
+ 25,
134
+ 26,
135
+ 27,
136
+ 28,
137
+ 29,
138
+ 31,
139
+ 58,
140
+ 59,
141
+ 60,
142
+ 61,
143
+ 62,
144
+ 63,
145
+ 90,
146
+ 91,
147
+ 92,
148
+ 93,
149
+ 359,
150
+ 503,
151
+ 522,
152
+ 542,
153
+ 873,
154
+ 893,
155
+ 902,
156
+ 918,
157
+ 922,
158
+ 931,
159
+ 1350,
160
+ 1853,
161
+ 1982,
162
+ 2460,
163
+ 2627,
164
+ 3246,
165
+ 3253,
166
+ 3268,
167
+ 3536,
168
+ 3846,
169
+ 3961,
170
+ 4183,
171
+ 4667,
172
+ 6585,
173
+ 6647,
174
+ 7273,
175
+ 9061,
176
+ 9383,
177
+ 10428,
178
+ 10929,
179
+ 11938,
180
+ 12033,
181
+ 12331,
182
+ 12562,
183
+ 13793,
184
+ 14157,
185
+ 14635,
186
+ 15265,
187
+ 15618,
188
+ 16553,
189
+ 16604,
190
+ 18362,
191
+ 18956,
192
+ 20075,
193
+ 21675,
194
+ 22520,
195
+ 26130,
196
+ 26161,
197
+ 26435,
198
+ 28279,
199
+ 29464,
200
+ 31650,
201
+ 32302,
202
+ 32470,
203
+ 36865,
204
+ 42863,
205
+ 47425,
206
+ 49870,
207
+ 50254,
208
+ 50258,
209
+ 50358,
210
+ 50359,
211
+ 50360,
212
+ 50361,
213
+ 50362
214
+ ],
215
+ "task_to_id": {
216
+ "transcribe": 50359,
217
+ "translate": 50358
218
+ },
219
+ "transformers_version": "4.31.0.dev0"
220
+ }
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6367d32c617a709ffc2be9926c6654966efdd6b4158a2d7e9ff3672e577b15a6
3
- size 3055736094
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cad5840b5ac1aec0398192fab7f06e682471d5636d33e4a8cee42517d8e5a151
3
+ size 3055741918