Hugging Face's logo

CAiRE
/
SER-wav2vec2-large-xlsr-53-eng-zho-adults

Audio Classification
Transformers
PyTorch
English
Chinese
wav2vec2
speech-emotion-recognition
Inference Endpoints
Model card Files Community
2
holylovenia commited on
Commit
1dc0f44
•
1 Parent(s): ad7469c

Add config.json

Browse files
Files changed (1) hide show
  1. config.json +146 -0
config.json ADDED
@@ -0,0 +1,146 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "facebook/wav2vec2-large-xlsr-53",
3
+ "activation_dropout": 0.0,
4
+ "adapter_kernel_size": 3,
5
+ "adapter_stride": 2,
6
+ "add_adapter": false,
7
+ "apply_spec_augment": true,
8
+ "architectures": [
9
+ "Wav2Vec2ForMultilabelSequenceClassification"
10
+ ],
11
+ "attention_dropout": 0.1,
12
+ "bos_token_id": 1,
13
+ "classifier_proj_size": 256,
14
+ "codevector_dim": 768,
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": 0.0,
55
+ "gradient_checkpointing": false,
56
+ "hidden_act": "gelu",
57
+ "hidden_dropout": 0.1,
58
+ "hidden_size": 1024,
59
+ "id2label": {
60
+ "0": "LABEL_0",
61
+ "1": "LABEL_1",
62
+ "2": "LABEL_2",
63
+ "3": "LABEL_3",
64
+ "4": "LABEL_4",
65
+ "5": "LABEL_5",
66
+ "6": "LABEL_6",
67
+ "7": "LABEL_7",
68
+ "8": "LABEL_8",
69
+ "9": "LABEL_9",
70
+ "10": "LABEL_10",
71
+ "11": "LABEL_11",
72
+ "12": "LABEL_12"
73
+ },
74
+ "initializer_range": 0.02,
75
+ "intermediate_size": 4096,
76
+ "label2id": {
77
+ "LABEL_0": 0,
78
+ "LABEL_1": 1,
79
+ "LABEL_10": 10,
80
+ "LABEL_11": 11,
81
+ "LABEL_12": 12,
82
+ "LABEL_2": 2,
83
+ "LABEL_3": 3,
84
+ "LABEL_4": 4,
85
+ "LABEL_5": 5,
86
+ "LABEL_6": 6,
87
+ "LABEL_7": 7,
88
+ "LABEL_8": 8,
89
+ "LABEL_9": 9
90
+ },
91
+ "layer_norm_eps": 1e-05,
92
+ "layerdrop": 0.1,
93
+ "mask_channel_length": 10,
94
+ "mask_channel_min_space": 1,
95
+ "mask_channel_other": 0.0,
96
+ "mask_channel_prob": 0.0,
97
+ "mask_channel_selection": "static",
98
+ "mask_feature_length": 10,
99
+ "mask_feature_min_masks": 0,
100
+ "mask_feature_prob": 0.0,
101
+ "mask_time_length": 10,
102
+ "mask_time_min_masks": 2,
103
+ "mask_time_min_space": 1,
104
+ "mask_time_other": 0.0,
105
+ "mask_time_prob": 0.075,
106
+ "mask_time_selection": "static",
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
+ "proj_codevector_dim": 768,
120
+ "tdnn_dilation": [
121
+ 1,
122
+ 2,
123
+ 3,
124
+ 1,
125
+ 1
126
+ ],
127
+ "tdnn_dim": [
128
+ 512,
129
+ 512,
130
+ 512,
131
+ 512,
132
+ 1500
133
+ ],
134
+ "tdnn_kernel": [
135
+ 5,
136
+ 3,
137
+ 3,
138
+ 1,
139
+ 1
140
+ ],
141
+ "torch_dtype": "float32",
142
+ "transformers_version": "4.25.1",
143
+ "use_weighted_layer_sum": false,
144
+ "vocab_size": 32,
145
+ "xvector_output_dim": 512
146
+ }