seba3y commited on
Commit
3c96321
·
1 Parent(s): 56240c9

Upload WhisperForAudioClassification

Browse files
Files changed (2) hide show
  1. config.json +167 -0
  2. model.safetensors +3 -0
config.json ADDED
@@ -0,0 +1,167 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/kaggle/input/audio-work-accuracy/audio_sent_acc/checkpoint-2376",
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": 100,
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
+ "id2label": {
43
+ "0": "Score: 0-4, Poor, clumsy and rigid pronunciation of the sentence as a whole, with serious pronunciation mistakes",
44
+ "1": "Score: 5-6, The overall pronunciation of the sentence is understandable, with many pronunciation mistakes and accent, but it does not affect the understanding of basic meanings",
45
+ "2": "Score: 7-8, The overall pronunciation of the sentence is good, with a few pronunciation mistakes",
46
+ "3": "Score: 9-10, The overall pronunciation of the sentence is excellent, with accurate phonology and no obvious pronunciation mistakes"
47
+ },
48
+ "init_std": 0.02,
49
+ "is_encoder_decoder": true,
50
+ "label2id": {
51
+ "Score: 0-4, Poor, clumsy and rigid pronunciation of the sentence as a whole, with serious pronunciation mistakes": 0,
52
+ "Score: 5-6, The overall pronunciation of the sentence is understandable, with many pronunciation mistakes and accent, but it does not affect the understanding of basic meanings": 1,
53
+ "Score: 7-8, The overall pronunciation of the sentence is good, with a few pronunciation mistakes": 2,
54
+ "Score: 9-10, The overall pronunciation of the sentence is excellent, with accurate phonology and no obvious pronunciation mistakes": 3
55
+ },
56
+ "mask_feature_length": 10,
57
+ "mask_feature_min_masks": 0,
58
+ "mask_feature_prob": 0.0,
59
+ "mask_time_length": 10,
60
+ "mask_time_min_masks": 2,
61
+ "mask_time_prob": 0.05,
62
+ "max_length": 448,
63
+ "max_source_positions": 500,
64
+ "max_target_positions": 448,
65
+ "median_filter_width": 7,
66
+ "model_type": "whisper",
67
+ "num_hidden_layers": 4,
68
+ "num_mel_bins": 80,
69
+ "pad_token_id": 50257,
70
+ "return_dict": false,
71
+ "scale_embedding": false,
72
+ "suppress_tokens": [
73
+ 1,
74
+ 2,
75
+ 7,
76
+ 8,
77
+ 9,
78
+ 10,
79
+ 14,
80
+ 25,
81
+ 26,
82
+ 27,
83
+ 28,
84
+ 29,
85
+ 31,
86
+ 58,
87
+ 59,
88
+ 60,
89
+ 61,
90
+ 62,
91
+ 63,
92
+ 90,
93
+ 91,
94
+ 92,
95
+ 93,
96
+ 359,
97
+ 503,
98
+ 522,
99
+ 542,
100
+ 873,
101
+ 893,
102
+ 902,
103
+ 918,
104
+ 922,
105
+ 931,
106
+ 1350,
107
+ 1853,
108
+ 1982,
109
+ 2460,
110
+ 2627,
111
+ 3246,
112
+ 3253,
113
+ 3268,
114
+ 3536,
115
+ 3846,
116
+ 3961,
117
+ 4183,
118
+ 4667,
119
+ 6585,
120
+ 6647,
121
+ 7273,
122
+ 9061,
123
+ 9383,
124
+ 10428,
125
+ 10929,
126
+ 11938,
127
+ 12033,
128
+ 12331,
129
+ 12562,
130
+ 13793,
131
+ 14157,
132
+ 14635,
133
+ 15265,
134
+ 15618,
135
+ 16553,
136
+ 16604,
137
+ 18362,
138
+ 18956,
139
+ 20075,
140
+ 21675,
141
+ 22520,
142
+ 26130,
143
+ 26161,
144
+ 26435,
145
+ 28279,
146
+ 29464,
147
+ 31650,
148
+ 32302,
149
+ 32470,
150
+ 36865,
151
+ 42863,
152
+ 47425,
153
+ 49870,
154
+ 50254,
155
+ 50258,
156
+ 50358,
157
+ 50359,
158
+ 50360,
159
+ 50361,
160
+ 50362
161
+ ],
162
+ "torch_dtype": "float32",
163
+ "transformers_version": "4.36.0",
164
+ "use_cache": true,
165
+ "use_weighted_layer_sum": true,
166
+ "vocab_size": 51865
167
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:00f5190284be75b6e6432feba55d64b61a6305280f0179bd103ad4f50df371b3
3
+ size 31460572