cifope commited on
Commit
b42320f
1 Parent(s): 8874b3a

Upload WhisperForConditionalGeneration

Browse files
Files changed (3) hide show
  1. config.json +104 -4
  2. generation_config.json +48 -12
  3. model.safetensors +1 -1
config.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "_name_or_path": "/content/whisper-small-wolof",
3
  "activation_dropout": 0.0,
4
  "activation_function": "gelu",
5
  "apply_spec_augment": false,
@@ -25,7 +25,20 @@
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,
31
  "mask_feature_length": 10,
@@ -43,9 +56,96 @@
43
  "num_mel_bins": 80,
44
  "pad_token_id": 50257,
45
  "scale_embedding": false,
46
- "suppress_tokens": [],
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
47
  "torch_dtype": "float32",
48
- "transformers_version": "4.42.4",
49
  "use_cache": true,
50
  "use_weighted_layer_sum": false,
51
  "vocab_size": 51865
 
1
  {
2
+ "_name_or_path": "openai/whisper-small",
3
  "activation_dropout": 0.0,
4
  "activation_function": "gelu",
5
  "apply_spec_augment": false,
 
25
  "encoder_layerdrop": 0.0,
26
  "encoder_layers": 12,
27
  "eos_token_id": 50257,
28
+ "forced_decoder_ids": [
29
+ [
30
+ 1,
31
+ 50259
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": 10,
 
56
  "num_mel_bins": 80,
57
  "pad_token_id": 50257,
58
  "scale_embedding": false,
59
+ "suppress_tokens": [
60
+ 1,
61
+ 2,
62
+ 7,
63
+ 8,
64
+ 9,
65
+ 10,
66
+ 14,
67
+ 25,
68
+ 26,
69
+ 27,
70
+ 28,
71
+ 29,
72
+ 31,
73
+ 58,
74
+ 59,
75
+ 60,
76
+ 61,
77
+ 62,
78
+ 63,
79
+ 90,
80
+ 91,
81
+ 92,
82
+ 93,
83
+ 359,
84
+ 503,
85
+ 522,
86
+ 542,
87
+ 873,
88
+ 893,
89
+ 902,
90
+ 918,
91
+ 922,
92
+ 931,
93
+ 1350,
94
+ 1853,
95
+ 1982,
96
+ 2460,
97
+ 2627,
98
+ 3246,
99
+ 3253,
100
+ 3268,
101
+ 3536,
102
+ 3846,
103
+ 3961,
104
+ 4183,
105
+ 4667,
106
+ 6585,
107
+ 6647,
108
+ 7273,
109
+ 9061,
110
+ 9383,
111
+ 10428,
112
+ 10929,
113
+ 11938,
114
+ 12033,
115
+ 12331,
116
+ 12562,
117
+ 13793,
118
+ 14157,
119
+ 14635,
120
+ 15265,
121
+ 15618,
122
+ 16553,
123
+ 16604,
124
+ 18362,
125
+ 18956,
126
+ 20075,
127
+ 21675,
128
+ 22520,
129
+ 26130,
130
+ 26161,
131
+ 26435,
132
+ 28279,
133
+ 29464,
134
+ 31650,
135
+ 32302,
136
+ 32470,
137
+ 36865,
138
+ 42863,
139
+ 47425,
140
+ 49870,
141
+ 50254,
142
+ 50258,
143
+ 50360,
144
+ 50361,
145
+ 50362
146
+ ],
147
  "torch_dtype": "float32",
148
+ "transformers_version": "4.43.0.dev0",
149
  "use_cache": true,
150
  "use_weighted_layer_sum": false,
151
  "vocab_size": 51865
generation_config.json CHANGED
@@ -1,4 +1,46 @@
1
  {
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
2
  "begin_suppress_tokens": [
3
  220,
4
  50257
@@ -6,16 +48,6 @@
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,
@@ -114,14 +146,17 @@
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
  "return_timestamps": false,
126
  "suppress_tokens": [
127
  1,
@@ -213,9 +248,10 @@
213
  50361,
214
  50362
215
  ],
 
216
  "task_to_id": {
217
  "transcribe": 50359,
218
  "translate": 50358
219
  },
220
- "transformers_version": "4.42.4"
221
  }
 
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
 
48
  "bos_token_id": 50257,
49
  "decoder_start_token_id": 50258,
50
  "eos_token_id": 50257,
 
 
 
 
 
 
 
 
 
 
51
  "is_multilingual": true,
52
  "lang_to_id": {
53
  "<|af|>": 50327,
 
146
  "<|ur|>": 50290,
147
  "<|uz|>": 50337,
148
  "<|vi|>": 50278,
149
+ "<|wo|>": 99,
150
  "<|yi|>": 50335,
151
  "<|yo|>": 50325,
152
  "<|zh|>": 50260
153
  },
154
+ "language": "wolof",
155
+ "max_initial_timestamp_index": 50,
156
  "max_length": 448,
157
  "no_timestamps_token_id": 50363,
158
  "pad_token_id": 50257,
159
+ "prev_sot_token_id": 50361,
160
  "return_timestamps": false,
161
  "suppress_tokens": [
162
  1,
 
248
  50361,
249
  50362
250
  ],
251
+ "task": "transcribe",
252
  "task_to_id": {
253
  "transcribe": 50359,
254
  "translate": 50358
255
  },
256
+ "transformers_version": "4.43.0.dev0"
257
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9f8d463c842d91ec428dad4160dac70846672dd3d6d0ce561bc922a097272a1b
3
  size 966995080
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:00de2ff569d923fbc09468d22856baefdfe3afa54ac66e7ae84fbe5af6e040b6
3
  size 966995080