XINGWEILIN commited on
Commit
5f72fde
·
verified ·
1 Parent(s): 733693e

Round 1 update

Browse files
Files changed (3) hide show
  1. config.json +61 -61
  2. generation_config.json +248 -248
  3. model.safetensors +1 -1
config.json CHANGED
@@ -1,61 +1,61 @@
1
- {
2
- "_name_or_path": "openai/whisper-tiny",
3
- "activation_dropout": 0.0,
4
- "activation_function": "gelu",
5
- "apply_spec_augment": false,
6
- "architectures": [
7
- "WhisperForConditionalGeneration"
8
- ],
9
- "attention_dropout": 0.0,
10
- "begin_suppress_tokens": null,
11
- "bos_token_id": 50257,
12
- "classifier_proj_size": 256,
13
- "d_model": 384,
14
- "decoder_attention_heads": 6,
15
- "decoder_ffn_dim": 1536,
16
- "decoder_layerdrop": 0.0,
17
- "decoder_layers": 4,
18
- "decoder_start_token_id": 50258,
19
- "dropout": 0.0,
20
- "encoder_attention_heads": 6,
21
- "encoder_ffn_dim": 1536,
22
- "encoder_layerdrop": 0.0,
23
- "encoder_layers": 4,
24
- "eos_token_id": 50257,
25
- "forced_decoder_ids": [
26
- [
27
- 1,
28
- 50259
29
- ],
30
- [
31
- 2,
32
- 50359
33
- ],
34
- [
35
- 3,
36
- 50363
37
- ]
38
- ],
39
- "init_std": 0.02,
40
- "is_encoder_decoder": true,
41
- "mask_feature_length": 10,
42
- "mask_feature_min_masks": 0,
43
- "mask_feature_prob": 0.0,
44
- "mask_time_length": 10,
45
- "mask_time_min_masks": 2,
46
- "mask_time_prob": 0.05,
47
- "max_length": null,
48
- "max_source_positions": 1500,
49
- "max_target_positions": 448,
50
- "median_filter_width": 7,
51
- "model_type": "whisper",
52
- "num_hidden_layers": 4,
53
- "num_mel_bins": 80,
54
- "pad_token_id": 50257,
55
- "scale_embedding": false,
56
- "torch_dtype": "float32",
57
- "transformers_version": "4.48.2",
58
- "use_cache": true,
59
- "use_weighted_layer_sum": false,
60
- "vocab_size": 51865
61
- }
 
1
+ {
2
+ "_name_or_path": "openai/whisper-tiny",
3
+ "activation_dropout": 0.0,
4
+ "activation_function": "gelu",
5
+ "apply_spec_augment": false,
6
+ "architectures": [
7
+ "WhisperForConditionalGeneration"
8
+ ],
9
+ "attention_dropout": 0.0,
10
+ "begin_suppress_tokens": null,
11
+ "bos_token_id": 50257,
12
+ "classifier_proj_size": 256,
13
+ "d_model": 384,
14
+ "decoder_attention_heads": 6,
15
+ "decoder_ffn_dim": 1536,
16
+ "decoder_layerdrop": 0.0,
17
+ "decoder_layers": 4,
18
+ "decoder_start_token_id": 50258,
19
+ "dropout": 0.0,
20
+ "encoder_attention_heads": 6,
21
+ "encoder_ffn_dim": 1536,
22
+ "encoder_layerdrop": 0.0,
23
+ "encoder_layers": 4,
24
+ "eos_token_id": 50257,
25
+ "forced_decoder_ids": [
26
+ [
27
+ 1,
28
+ 50259
29
+ ],
30
+ [
31
+ 2,
32
+ 50359
33
+ ],
34
+ [
35
+ 3,
36
+ 50363
37
+ ]
38
+ ],
39
+ "init_std": 0.02,
40
+ "is_encoder_decoder": true,
41
+ "mask_feature_length": 10,
42
+ "mask_feature_min_masks": 0,
43
+ "mask_feature_prob": 0.0,
44
+ "mask_time_length": 10,
45
+ "mask_time_min_masks": 2,
46
+ "mask_time_prob": 0.05,
47
+ "max_length": null,
48
+ "max_source_positions": 1500,
49
+ "max_target_positions": 448,
50
+ "median_filter_width": 7,
51
+ "model_type": "whisper",
52
+ "num_hidden_layers": 4,
53
+ "num_mel_bins": 80,
54
+ "pad_token_id": 50257,
55
+ "scale_embedding": false,
56
+ "torch_dtype": "float32",
57
+ "transformers_version": "4.47.1",
58
+ "use_cache": true,
59
+ "use_weighted_layer_sum": false,
60
+ "vocab_size": 51865
61
+ }
generation_config.json CHANGED
@@ -1,248 +1,248 @@
1
- {
2
- "alignment_heads": [
3
- [
4
- 2,
5
- 2
6
- ],
7
- [
8
- 3,
9
- 0
10
- ],
11
- [
12
- 3,
13
- 2
14
- ],
15
- [
16
- 3,
17
- 3
18
- ],
19
- [
20
- 3,
21
- 4
22
- ],
23
- [
24
- 3,
25
- 5
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": 50,
148
- "max_length": 448,
149
- "no_timestamps_token_id": 50363,
150
- "pad_token_id": 50257,
151
- "prev_sot_token_id": 50361,
152
- "return_timestamps": false,
153
- "suppress_tokens": [
154
- 1,
155
- 2,
156
- 7,
157
- 8,
158
- 9,
159
- 10,
160
- 14,
161
- 25,
162
- 26,
163
- 27,
164
- 28,
165
- 29,
166
- 31,
167
- 58,
168
- 59,
169
- 60,
170
- 61,
171
- 62,
172
- 63,
173
- 90,
174
- 91,
175
- 92,
176
- 93,
177
- 359,
178
- 503,
179
- 522,
180
- 542,
181
- 873,
182
- 893,
183
- 902,
184
- 918,
185
- 922,
186
- 931,
187
- 1350,
188
- 1853,
189
- 1982,
190
- 2460,
191
- 2627,
192
- 3246,
193
- 3253,
194
- 3268,
195
- 3536,
196
- 3846,
197
- 3961,
198
- 4183,
199
- 4667,
200
- 6585,
201
- 6647,
202
- 7273,
203
- 9061,
204
- 9383,
205
- 10428,
206
- 10929,
207
- 11938,
208
- 12033,
209
- 12331,
210
- 12562,
211
- 13793,
212
- 14157,
213
- 14635,
214
- 15265,
215
- 15618,
216
- 16553,
217
- 16604,
218
- 18362,
219
- 18956,
220
- 20075,
221
- 21675,
222
- 22520,
223
- 26130,
224
- 26161,
225
- 26435,
226
- 28279,
227
- 29464,
228
- 31650,
229
- 32302,
230
- 32470,
231
- 36865,
232
- 42863,
233
- 47425,
234
- 49870,
235
- 50254,
236
- 50258,
237
- 50358,
238
- 50359,
239
- 50360,
240
- 50361,
241
- 50362
242
- ],
243
- "task_to_id": {
244
- "transcribe": 50359,
245
- "translate": 50358
246
- },
247
- "transformers_version": "4.48.2"
248
- }
 
1
+ {
2
+ "alignment_heads": [
3
+ [
4
+ 2,
5
+ 2
6
+ ],
7
+ [
8
+ 3,
9
+ 0
10
+ ],
11
+ [
12
+ 3,
13
+ 2
14
+ ],
15
+ [
16
+ 3,
17
+ 3
18
+ ],
19
+ [
20
+ 3,
21
+ 4
22
+ ],
23
+ [
24
+ 3,
25
+ 5
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": 50,
148
+ "max_length": 448,
149
+ "no_timestamps_token_id": 50363,
150
+ "pad_token_id": 50257,
151
+ "prev_sot_token_id": 50361,
152
+ "return_timestamps": false,
153
+ "suppress_tokens": [
154
+ 1,
155
+ 2,
156
+ 7,
157
+ 8,
158
+ 9,
159
+ 10,
160
+ 14,
161
+ 25,
162
+ 26,
163
+ 27,
164
+ 28,
165
+ 29,
166
+ 31,
167
+ 58,
168
+ 59,
169
+ 60,
170
+ 61,
171
+ 62,
172
+ 63,
173
+ 90,
174
+ 91,
175
+ 92,
176
+ 93,
177
+ 359,
178
+ 503,
179
+ 522,
180
+ 542,
181
+ 873,
182
+ 893,
183
+ 902,
184
+ 918,
185
+ 922,
186
+ 931,
187
+ 1350,
188
+ 1853,
189
+ 1982,
190
+ 2460,
191
+ 2627,
192
+ 3246,
193
+ 3253,
194
+ 3268,
195
+ 3536,
196
+ 3846,
197
+ 3961,
198
+ 4183,
199
+ 4667,
200
+ 6585,
201
+ 6647,
202
+ 7273,
203
+ 9061,
204
+ 9383,
205
+ 10428,
206
+ 10929,
207
+ 11938,
208
+ 12033,
209
+ 12331,
210
+ 12562,
211
+ 13793,
212
+ 14157,
213
+ 14635,
214
+ 15265,
215
+ 15618,
216
+ 16553,
217
+ 16604,
218
+ 18362,
219
+ 18956,
220
+ 20075,
221
+ 21675,
222
+ 22520,
223
+ 26130,
224
+ 26161,
225
+ 26435,
226
+ 28279,
227
+ 29464,
228
+ 31650,
229
+ 32302,
230
+ 32470,
231
+ 36865,
232
+ 42863,
233
+ 47425,
234
+ 49870,
235
+ 50254,
236
+ 50258,
237
+ 50358,
238
+ 50359,
239
+ 50360,
240
+ 50361,
241
+ 50362
242
+ ],
243
+ "task_to_id": {
244
+ "transcribe": 50359,
245
+ "translate": 50358
246
+ },
247
+ "transformers_version": "4.47.1"
248
+ }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e42e9d2895d7d29c10fe97df5fcfdbbc5dc50c0b9a5e4439f4b44932a2eef839
3
  size 151061672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7a48da9cf470c2176ea91caa27993244c583b50ef839e3c159b1b1c92e0fc853
3
  size 151061672