Hugging Face's logo

sanjitaa
/
base-whisper

Automatic Speech Recognition
Transformers
PyTorch
TensorFlow
Safetensors
whisper
Inference Endpoints
Model card Files Community
sanjitaa commited on
Commit
4fc2edf
•
1 Parent(s): b60c8c8

update config.json

Browse files
Files changed (1) hide show
  1. config.json +140 -135
config.json CHANGED
@@ -1,139 +1,144 @@
1
  {
2
- "_name_or_path": "sanjitaa/whisper_model",
3
- "activation_dropout": 0.0,
4
- "activation_function": "gelu",
5
- "architectures": [
6
- "WhisperForConditionalGeneration"
7
- ],
8
- "attention_dropout": 0.0,
9
- "begin_suppress_tokens": [
10
- 220,
11
- 50256
12
- ],
13
- "bos_token_id": 50257,
14
- "d_model": 1024,
15
- "decoder_attention_heads": 16,
16
- "decoder_ffn_dim": 4096,
17
- "decoder_layerdrop": 0.0,
18
- "decoder_layers": 24,
19
- "decoder_start_token_id": 50257,
20
- "dropout": 0.0,
21
- "encoder_attention_heads": 16,
22
- "encoder_ffn_dim": 4096,
23
- "encoder_layerdrop": 0.0,
24
- "encoder_layers": 24,
25
- "eos_token_id": 50256,
26
- "forced_decoder_ids": [
27
- [
28
- 1,
29
- 50362
30
- ]
31
- ],
32
- "init_std": 0.02,
33
- "is_encoder_decoder": true,
34
- "max_length": 448,
35
- "max_source_positions": 1500,
36
- "max_target_positions": 448,
37
- "model_type": "whisper",
38
- "num_hidden_layers": 24,
39
- "num_mel_bins": 80,
40
- "pad_token_id": 50256,
41
- "scale_embedding": false,
42
- "suppress_tokens": [
43
  1,
 
 
 
44
  2,
45
- 7,
46
- 8,
47
- 9,
48
- 10,
49
- 14,
50
- 25,
51
- 26,
52
- 27,
53
- 28,
54
- 29,
55
- 31,
56
- 58,
57
- 59,
58
- 60,
59
- 61,
60
- 62,
61
- 63,
62
- 90,
63
- 91,
64
- 92,
65
- 93,
66
- 357,
67
- 366,
68
- 438,
69
- 532,
70
- 685,
71
- 705,
72
- 796,
73
- 930,
74
- 1058,
75
- 1220,
76
- 1267,
77
- 1279,
78
- 1303,
79
- 1343,
80
- 1377,
81
- 1391,
82
- 1635,
83
- 1782,
84
- 1875,
85
- 2162,
86
- 2361,
87
- 2488,
88
- 3467,
89
- 4008,
90
- 4211,
91
- 4600,
92
- 4808,
93
- 5299,
94
- 5855,
95
- 6329,
96
- 7203,
97
- 9609,
98
- 9959,
99
- 10563,
100
- 10786,
101
- 11420,
102
- 11709,
103
- 11907,
104
- 13163,
105
- 13697,
106
- 13700,
107
- 14808,
108
- 15306,
109
- 16410,
110
- 16791,
111
- 17992,
112
- 19203,
113
- 19510,
114
- 20724,
115
- 22305,
116
- 22935,
117
- 27007,
118
- 30109,
119
- 30420,
120
- 33409,
121
- 34949,
122
- 40283,
123
- 40493,
124
- 40549,
125
- 47282,
126
- 49146,
127
- 50257,
128
- 50357,
129
- 50358,
130
- 50359,
131
- 50360,
132
- 50361
133
  ],
134
- "torch_dtype": "float32",
135
- "transformers_version": "4.27.0.dev0",
136
- "use_cache": true,
137
- "vocab_size": 51864
138
- }
139
-
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  {
2
+ "_name_or_path": "sanjitaa/base-whisper",
3
+ "activation_dropout": 0.0,
4
+ "activation_function": "gelu",
5
+ "architectures": [
6
+ "WhisperForConditionalGeneration"
7
+ ],
8
+ "attention_dropout": 0.0,
9
+ "begin_suppress_tokens": [
10
+ 220,
11
+ 50257
12
+ ],
13
+ "bos_token_id": 50257,
14
+ "d_model": 512,
15
+ "decoder_attention_heads": 8,
16
+ "decoder_ffn_dim": 2048,
17
+ "decoder_layerdrop": 0.0,
18
+ "decoder_layers": 6,
19
+ "decoder_start_token_id": 50258,
20
+ "dropout": 0.0,
21
+ "encoder_attention_heads": 8,
22
+ "encoder_ffn_dim": 2048,
23
+ "encoder_layerdrop": 0.0,
24
+ "encoder_layers": 6,
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": 6,
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
+ 50358,
135
+ 50359,
136
+ 50360,
137
+ 50361,
138
+ 50362
139
+ ],
140
+ "torch_dtype": "float32",
141
+ "transformers_version": "4.27.0.dev0",
142
+ "use_cache": true,
143
+ "vocab_size": 51865
144
+ }