Hugging Face's logo

padmalcom
/
wav2vec2-large-nonverbalvocalization-classification

Audio Classification Transformers PyTorch
multilingual wav2vec2 voice classification vocalization speech audio Inference Endpoints
Model card Files Community
1
padmalcom commited on
Commit
30a8a5d
•
1 Parent(s): bfae427

Upload config.json

Browse files
Files changed (1) hide show
  1. config.json +148 -0
config.json ADDED
@@ -0,0 +1,148 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "facebook/wav2vec2-large-960h-lv60-self",
3
+ "activation_dropout": 0.1,
4
+ "adapter_kernel_size": 3,
5
+ "adapter_stride": 2,
6
+ "add_adapter": false,
7
+ "apply_spec_augment": true,
8
+ "architectures": [
9
+ "Wav2Vec2ForSpeechClassification"
10
+ ],
11
+ "attention_dropout": 0.1,
12
+ "bos_token_id": 1,
13
+ "classifier_proj_size": 256,
14
+ "codevector_dim": 256,
15
+ "contrastive_logits_temperature": 0.1,
16
+ "conv_bias": true,
17
+ "conv_dim": [
18
+ 512,
19
+ 512,
20
+ 512,
21
+ 512,
22
+ 512,
23
+ 512,
24
+ 512
25
+ ],
26
+ "conv_kernel": [
27
+ 10,
28
+ 3,
29
+ 3,
30
+ 3,
31
+ 3,
32
+ 2,
33
+ 2
34
+ ],
35
+ "conv_stride": [
36
+ 5,
37
+ 2,
38
+ 2,
39
+ 2,
40
+ 2,
41
+ 2,
42
+ 2
43
+ ],
44
+ "ctc_loss_reduction": "sum",
45
+ "ctc_zero_infinity": false,
46
+ "diversity_loss_weight": 0.1,
47
+ "do_stable_layer_norm": true,
48
+ "eos_token_id": 2,
49
+ "feat_extract_activation": "gelu",
50
+ "feat_extract_dropout": 0.0,
51
+ "feat_extract_norm": "layer",
52
+ "feat_proj_dropout": 0.1,
53
+ "feat_quantizer_dropout": 0.0,
54
+ "final_dropout": 0.1,
55
+ "finetuning_task": "wav2vec2_clf",
56
+ "gradient_checkpointing": false,
57
+ "hidden_act": "gelu",
58
+ "hidden_dropout": 0.1,
59
+ "hidden_dropout_prob": 0.1,
60
+ "hidden_size": 1024,
61
+ "id2label": {
62
+ "0": "teeth-chattering",
63
+ "1": "teeth-grinding",
64
+ "2": "tongue-clicking",
65
+ "3": "nose-blowing",
66
+ "4": "coughing",
67
+ "5": "yawning",
68
+ "6": "throat-clearing",
69
+ "7": "sighing",
70
+ "8": "lip-popping",
71
+ "9": "lip-smacking",
72
+ "10": "panting",
73
+ "11": "crying",
74
+ "12": "laughing",
75
+ "13": "sneezing",
76
+ "14": "moaning",
77
+ "15": "screaming"
78
+ },
79
+ "initializer_range": 0.02,
80
+ "intermediate_size": 4096,
81
+ "label2id": {
82
+ "coughing": 4,
83
+ "crying": 11,
84
+ "laughing": 12,
85
+ "lip-popping": 8,
86
+ "lip-smacking": 9,
87
+ "moaning": 14,
88
+ "nose-blowing": 3,
89
+ "panting": 10,
90
+ "screaming": 15,
91
+ "sighing": 7,
92
+ "sneezing": 13,
93
+ "teeth-chattering": 0,
94
+ "teeth-grinding": 1,
95
+ "throat-clearing": 6,
96
+ "tongue-clicking": 2,
97
+ "yawning": 5
98
+ },
99
+ "layer_norm_eps": 1e-05,
100
+ "layerdrop": 0.1,
101
+ "mask_feature_length": 10,
102
+ "mask_feature_min_masks": 0,
103
+ "mask_feature_prob": 0.0,
104
+ "mask_time_length": 10,
105
+ "mask_time_min_masks": 2,
106
+ "mask_time_prob": 0.05,
107
+ "model_type": "wav2vec2",
108
+ "num_adapter_layers": 3,
109
+ "num_attention_heads": 16,
110
+ "num_codevector_groups": 2,
111
+ "num_codevectors_per_group": 320,
112
+ "num_conv_pos_embedding_groups": 16,
113
+ "num_conv_pos_embeddings": 128,
114
+ "num_feat_extract_layers": 7,
115
+ "num_hidden_layers": 24,
116
+ "num_negatives": 100,
117
+ "output_hidden_size": 1024,
118
+ "pad_token_id": 0,
119
+ "pooling_mode": "mean",
120
+ "problem_type": "single_label_classification",
121
+ "proj_codevector_dim": 256,
122
+ "tdnn_dilation": [
123
+ 1,
124
+ 2,
125
+ 3,
126
+ 1,
127
+ 1
128
+ ],
129
+ "tdnn_dim": [
130
+ 512,
131
+ 512,
132
+ 512,
133
+ 512,
134
+ 1500
135
+ ],
136
+ "tdnn_kernel": [
137
+ 5,
138
+ 3,
139
+ 3,
140
+ 1,
141
+ 1
142
+ ],
143
+ "torch_dtype": "float32",
144
+ "transformers_version": "4.25.1",
145
+ "use_weighted_layer_sum": false,
146
+ "vocab_size": 32,
147
+ "xvector_output_dim": 512
148
+ }