Hugging Face's logo

panda199393
/
speech1

Audio Classification
Transformers
Safetensors
whisper
Inference Endpoints
Model card Files Community
panda199393 commited on
Commit
b1e9176
•
1 Parent(s): df1b5da

Upload WhisperForAudioClassification

Browse files
Files changed (2) hide show
  1. config.json +154 -154
  2. model.safetensors +2 -2
config.json CHANGED
@@ -1,154 +1,154 @@
1
- {
2
- "_name_or_path": "openai/whisper-medium",
3
- "activation_dropout": 0.0,
4
- "activation_function": "gelu",
5
- "apply_spec_augment": false,
6
- "architectures": [
7
- "WhisperForAudioClassification"
8
- ],
9
- "attention_dropout": 0.0,
10
- "begin_suppress_tokens": [
11
- 220,
12
- 50257
13
- ],
14
- "bos_token_id": 50257,
15
- "classifier_proj_size": 256,
16
- "d_model": 1024,
17
- "decoder_attention_heads": 16,
18
- "decoder_ffn_dim": 4096,
19
- "decoder_layerdrop": 0.0,
20
- "decoder_layers": 24,
21
- "decoder_start_token_id": 50258,
22
- "dropout": 0.0,
23
- "encoder_attention_heads": 16,
24
- "encoder_ffn_dim": 4096,
25
- "encoder_layerdrop": 0.0,
26
- "encoder_layers": 24,
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,
45
- "mask_feature_min_masks": 0,
46
- "mask_feature_prob": 0.0,
47
- "mask_time_length": 10,
48
- "mask_time_min_masks": 2,
49
- "mask_time_prob": 0.05,
50
- "max_length": 448,
51
- "max_source_positions": 1500,
52
- "max_target_positions": 448,
53
- "median_filter_width": 7,
54
- "model_type": "whisper",
55
- "num_hidden_layers": 24,
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
- 50358,
144
- 50359,
145
- 50360,
146
- 50361,
147
- 50362
148
- ],
149
- "torch_dtype": "float32",
150
- "transformers_version": "4.41.1",
151
- "use_cache": true,
152
- "use_weighted_layer_sum": false,
153
- "vocab_size": 51865
154
- }
 
1
+ {
2
+ "_name_or_path": "checkpoints-whisper/temp",
3
+ "activation_dropout": 0.0,
4
+ "activation_function": "gelu",
5
+ "apply_spec_augment": false,
6
+ "architectures": [
7
+ "WhisperForAudioClassification"
8
+ ],
9
+ "attention_dropout": 0.0,
10
+ "begin_suppress_tokens": [
11
+ 220,
12
+ 50257
13
+ ],
14
+ "bos_token_id": 50257,
15
+ "classifier_proj_size": 256,
16
+ "d_model": 384,
17
+ "decoder_attention_heads": 6,
18
+ "decoder_ffn_dim": 1536,
19
+ "decoder_layerdrop": 0.0,
20
+ "decoder_layers": 4,
21
+ "decoder_start_token_id": 50258,
22
+ "dropout": 0.0,
23
+ "encoder_attention_heads": 6,
24
+ "encoder_ffn_dim": 1536,
25
+ "encoder_layerdrop": 0.0,
26
+ "encoder_layers": 4,
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,
45
+ "mask_feature_min_masks": 0,
46
+ "mask_feature_prob": 0.0,
47
+ "mask_time_length": 10,
48
+ "mask_time_min_masks": 2,
49
+ "mask_time_prob": 0.05,
50
+ "max_length": 448,
51
+ "max_source_positions": 1500,
52
+ "max_target_positions": 448,
53
+ "median_filter_width": 7,
54
+ "model_type": "whisper",
55
+ "num_hidden_layers": 4,
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
+ 50358,
144
+ 50359,
145
+ 50360,
146
+ 50361,
147
+ 50362
148
+ ],
149
+ "torch_dtype": "float32",
150
+ "transformers_version": "4.41.1",
151
+ "use_cache": true,
152
+ "use_weighted_layer_sum": false,
153
+ "vocab_size": 51865
154
+ }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bf236f7f1591f950aab1648b3497708042ac6645d9a5e5bdf29105f023497300
3
- size 1229957888
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3f2c8579b796b69cfcd57fe9bf18c0db53cd8fd41780993009ffd537aa111591
3
+ size 33237160