Hugging Face's logo

r-f
/
wav2vec-english-speech-emotion-recognition

Transformers
PyTorch
wav2vec2
Generated from Trainer
Inference Endpoints
Model card Files Community
3
r-f commited on
Commit
bdd11d6
•
1 Parent(s): 23b1718

Upload config.json

Browse files
Files changed (1) hide show
  1. config.json +136 -0
config.json ADDED
@@ -0,0 +1,136 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "jonatasgrosman/wav2vec2-large-xlsr-53-english",
3
+ "activation_dropout": 0.05,
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": "mean",
45
+ "ctc_zero_infinity": true,
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": 0.05,
53
+ "feat_quantizer_dropout": 0.0,
54
+ "final_dropout": 0.0,
55
+ "finetuning_task": "wav2vec2_clf",
56
+ "hidden_act": "gelu",
57
+ "hidden_dropout": 0.05,
58
+ "hidden_size": 1024,
59
+ "id2label": {
60
+ "0": "angry",
61
+ "1": "disgust",
62
+ "2": "fear",
63
+ "3": "happy",
64
+ "4": "neutral",
65
+ "5": "sad",
66
+ "6": "surprise"
67
+ },
68
+ "initializer_range": 0.02,
69
+ "intermediate_size": 4096,
70
+ "label2id": {
71
+ "angry": 0,
72
+ "disgust": 1,
73
+ "fear": 2,
74
+ "happy": 3,
75
+ "neutral": 4,
76
+ "sad": 5,
77
+ "surprise": 6
78
+ },
79
+ "layer_norm_eps": 1e-05,
80
+ "layerdrop": 0.05,
81
+ "mask_channel_length": 10,
82
+ "mask_channel_min_space": 1,
83
+ "mask_channel_other": 0.0,
84
+ "mask_channel_prob": 0.0,
85
+ "mask_channel_selection": "static",
86
+ "mask_feature_length": 10,
87
+ "mask_feature_min_masks": 0,
88
+ "mask_feature_prob": 0.0,
89
+ "mask_time_length": 10,
90
+ "mask_time_min_masks": 2,
91
+ "mask_time_min_space": 1,
92
+ "mask_time_other": 0.0,
93
+ "mask_time_prob": 0.05,
94
+ "mask_time_selection": "static",
95
+ "model_type": "wav2vec2",
96
+ "num_adapter_layers": 3,
97
+ "num_attention_heads": 16,
98
+ "num_codevector_groups": 2,
99
+ "num_codevectors_per_group": 320,
100
+ "num_conv_pos_embedding_groups": 16,
101
+ "num_conv_pos_embeddings": 128,
102
+ "num_feat_extract_layers": 7,
103
+ "num_hidden_layers": 24,
104
+ "num_negatives": 100,
105
+ "output_hidden_size": 1024,
106
+ "pad_token_id": 0,
107
+ "pooling_mode": "mean",
108
+ "problem_type": "single_label_classification",
109
+ "proj_codevector_dim": 256,
110
+ "tdnn_dilation": [
111
+ 1,
112
+ 2,
113
+ 3,
114
+ 1,
115
+ 1
116
+ ],
117
+ "tdnn_dim": [
118
+ 512,
119
+ 512,
120
+ 512,
121
+ 512,
122
+ 1500
123
+ ],
124
+ "tdnn_kernel": [
125
+ 5,
126
+ 3,
127
+ 3,
128
+ 1,
129
+ 1
130
+ ],
131
+ "torch_dtype": "float32",
132
+ "transformers_version": "4.22.1",
133
+ "use_weighted_layer_sum": false,
134
+ "vocab_size": 33,
135
+ "xvector_output_dim": 512
136
+ }