EricChang commited on
Commit
7268858
1 Parent(s): 6b4315d

Update config.json

Browse files
Files changed (1) hide show
  1. config.json +113 -22
config.json CHANGED
@@ -1,8 +1,7 @@
1
  {
2
- "_name_or_path": "openai/whisper-large-v2",
3
  "activation_dropout": 0.0,
4
  "activation_function": "gelu",
5
- "apply_spec_augment": false,
6
  "architectures": [
7
  "WhisperForConditionalGeneration"
8
  ],
@@ -12,40 +11,132 @@
12
  50257
13
  ],
14
  "bos_token_id": 50257,
15
- "classifier_proj_size": 256,
16
- "d_model": 1280,
17
- "decoder_attention_heads": 20,
18
- "decoder_ffn_dim": 5120,
19
  "decoder_layerdrop": 0.0,
20
- "decoder_layers": 32,
21
  "decoder_start_token_id": 50258,
22
  "dropout": 0.0,
23
- "encoder_attention_heads": 20,
24
- "encoder_ffn_dim": 5120,
25
  "encoder_layerdrop": 0.0,
26
- "encoder_layers": 32,
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,
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
  "model_type": "whisper",
41
- "num_hidden_layers": 32,
42
  "num_mel_bins": 80,
43
  "pad_token_id": 50257,
44
  "scale_embedding": false,
45
- "suppress_tokens": [],
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
46
  "torch_dtype": "float32",
47
- "transformers_version": "4.27.4",
48
- "use_cache": false,
49
- "use_weighted_layer_sum": false,
50
  "vocab_size": 51865
51
  }
 
1
  {
2
+ "_name_or_path": "openai/whisper-small",
3
  "activation_dropout": 0.0,
4
  "activation_function": "gelu",
 
5
  "architectures": [
6
  "WhisperForConditionalGeneration"
7
  ],
 
11
  50257
12
  ],
13
  "bos_token_id": 50257,
14
+ "d_model": 768,
15
+ "decoder_attention_heads": 12,
16
+ "decoder_ffn_dim": 3072,
 
17
  "decoder_layerdrop": 0.0,
18
+ "decoder_layers": 12,
19
  "decoder_start_token_id": 50258,
20
  "dropout": 0.0,
21
+ "encoder_attention_heads": 12,
22
+ "encoder_ffn_dim": 3072,
23
  "encoder_layerdrop": 0.0,
24
+ "encoder_layers": 12,
25
  "eos_token_id": 50257,
26
+ "forced_decoder_ids": [
27
+ [
28
+ 1,
29
+ 50259
30
+ ],
31
+ [
32
+ 2,
33
+ 50359
34
+ ],
35
+ [
36
+ 3,
37
+ 50363
38
+ ]
39
+ ],
40
  "init_std": 0.02,
41
  "is_encoder_decoder": true,
 
 
 
 
 
 
42
  "max_length": 448,
43
  "max_source_positions": 1500,
44
  "max_target_positions": 448,
45
  "model_type": "whisper",
46
+ "num_hidden_layers": 12,
47
  "num_mel_bins": 80,
48
  "pad_token_id": 50257,
49
  "scale_embedding": false,
50
+ "suppress_tokens": [
51
+ 1,
52
+ 2,
53
+ 7,
54
+ 8,
55
+ 9,
56
+ 10,
57
+ 14,
58
+ 25,
59
+ 26,
60
+ 27,
61
+ 28,
62
+ 29,
63
+ 31,
64
+ 58,
65
+ 59,
66
+ 60,
67
+ 61,
68
+ 62,
69
+ 63,
70
+ 90,
71
+ 91,
72
+ 92,
73
+ 93,
74
+ 359,
75
+ 503,
76
+ 522,
77
+ 542,
78
+ 873,
79
+ 893,
80
+ 902,
81
+ 918,
82
+ 922,
83
+ 931,
84
+ 1350,
85
+ 1853,
86
+ 1982,
87
+ 2460,
88
+ 2627,
89
+ 3246,
90
+ 3253,
91
+ 3268,
92
+ 3536,
93
+ 3846,
94
+ 3961,
95
+ 4183,
96
+ 4667,
97
+ 6585,
98
+ 6647,
99
+ 7273,
100
+ 9061,
101
+ 9383,
102
+ 10428,
103
+ 10929,
104
+ 11938,
105
+ 12033,
106
+ 12331,
107
+ 12562,
108
+ 13793,
109
+ 14157,
110
+ 14635,
111
+ 15265,
112
+ 15618,
113
+ 16553,
114
+ 16604,
115
+ 18362,
116
+ 18956,
117
+ 20075,
118
+ 21675,
119
+ 22520,
120
+ 26130,
121
+ 26161,
122
+ 26435,
123
+ 28279,
124
+ 29464,
125
+ 31650,
126
+ 32302,
127
+ 32470,
128
+ 36865,
129
+ 42863,
130
+ 47425,
131
+ 49870,
132
+ 50254,
133
+ 50258,
134
+ 50360,
135
+ 50361,
136
+ 50362
137
+ ],
138
  "torch_dtype": "float32",
139
+ "transformers_version": "4.27.0.dev0",
140
+ "use_cache": true,
 
141
  "vocab_size": 51865
142
  }