Hugging Face's logo

octanove
/
mosla-whisper-spkid-zho

Audio Classification
Transformers
PyTorch
whisper
Inference Endpoints
Model card Files Community
Jotanner commited on
Commit
369928c
•
1 Parent(s): 1bd648c

Upload WhisperForAudioClassification

Browse files
Files changed (2) hide show
  1. config.json +163 -0
  2. pytorch_model.bin +3 -0
config.json ADDED
@@ -0,0 +1,163 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "whisper-speaker-id-zho/checkpoint-876",
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": 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": [
29
+ [
30
+ 1,
31
+ 50259
32
+ ],
33
+ [
34
+ 2,
35
+ 50359
36
+ ],
37
+ [
38
+ 3,
39
+ 50363
40
+ ]
41
+ ],
42
+ "id2label": {
43
+ "0": "t",
44
+ "1": "s",
45
+ "2": "o"
46
+ },
47
+ "init_std": 0.02,
48
+ "is_encoder_decoder": true,
49
+ "label2id": {
50
+ "o": 2,
51
+ "s": 1,
52
+ "t": 0
53
+ },
54
+ "mask_feature_length": 10,
55
+ "mask_feature_min_masks": 0,
56
+ "mask_feature_prob": 0.0,
57
+ "mask_time_length": 10,
58
+ "mask_time_min_masks": 2,
59
+ "mask_time_prob": 0.05,
60
+ "max_length": 448,
61
+ "max_source_positions": 1500,
62
+ "max_target_positions": 448,
63
+ "model_type": "whisper",
64
+ "num_hidden_layers": 32,
65
+ "num_mel_bins": 80,
66
+ "pad_token_id": 50257,
67
+ "scale_embedding": false,
68
+ "suppress_tokens": [
69
+ 1,
70
+ 2,
71
+ 7,
72
+ 8,
73
+ 9,
74
+ 10,
75
+ 14,
76
+ 25,
77
+ 26,
78
+ 27,
79
+ 28,
80
+ 29,
81
+ 31,
82
+ 58,
83
+ 59,
84
+ 60,
85
+ 61,
86
+ 62,
87
+ 63,
88
+ 90,
89
+ 91,
90
+ 92,
91
+ 93,
92
+ 359,
93
+ 503,
94
+ 522,
95
+ 542,
96
+ 873,
97
+ 893,
98
+ 902,
99
+ 918,
100
+ 922,
101
+ 931,
102
+ 1350,
103
+ 1853,
104
+ 1982,
105
+ 2460,
106
+ 2627,
107
+ 3246,
108
+ 3253,
109
+ 3268,
110
+ 3536,
111
+ 3846,
112
+ 3961,
113
+ 4183,
114
+ 4667,
115
+ 6585,
116
+ 6647,
117
+ 7273,
118
+ 9061,
119
+ 9383,
120
+ 10428,
121
+ 10929,
122
+ 11938,
123
+ 12033,
124
+ 12331,
125
+ 12562,
126
+ 13793,
127
+ 14157,
128
+ 14635,
129
+ 15265,
130
+ 15618,
131
+ 16553,
132
+ 16604,
133
+ 18362,
134
+ 18956,
135
+ 20075,
136
+ 21675,
137
+ 22520,
138
+ 26130,
139
+ 26161,
140
+ 26435,
141
+ 28279,
142
+ 29464,
143
+ 31650,
144
+ 32302,
145
+ 32470,
146
+ 36865,
147
+ 42863,
148
+ 47425,
149
+ 49870,
150
+ 50254,
151
+ 50258,
152
+ 50358,
153
+ 50359,
154
+ 50360,
155
+ 50361,
156
+ 50362
157
+ ],
158
+ "torch_dtype": "float32",
159
+ "transformers_version": "4.27.4",
160
+ "use_cache": false,
161
+ "use_weighted_layer_sum": false,
162
+ "vocab_size": 51865
163
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:09e4c3bf77e0a99977b330c86ff77bfd718de38d89ae6ca21e50e340366f80f3
3
+ size 2548606507