Hugging Face's logo

audeering
/
wav2vec2-large-robust-12-ft-emotion-msp-dim

Audio Classification
Transformers
PyTorch
Safetensors
English
wav2vec2
speech
audio
emotion-recognition
Inference Endpoints
Model card Files Community
11
frankenjoe commited on
Commit
fb0a1d7
•
1 Parent(s): 821a48e

add model

Browse files
Files changed (2) hide show
  1. config.json +122 -0
  2. pytorch_model.bin +3 -0
config.json ADDED
@@ -0,0 +1,122 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "torch",
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": 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": 0.1,
55
+ "finetuning_task": "wav2vec2_reg",
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": "LABEL_0",
63
+ "1": "LABEL_1",
64
+ "2": "LABEL_2"
65
+ },
66
+ "initializer_range": 0.02,
67
+ "intermediate_size": 4096,
68
+ "label2id": {
69
+ "LABEL_0": 0,
70
+ "LABEL_1": 1,
71
+ "LABEL_2": 2
72
+ },
73
+ "layer_norm_eps": 1e-05,
74
+ "layerdrop": 0.1,
75
+ "mask_feature_length": 10,
76
+ "mask_feature_min_masks": 0,
77
+ "mask_feature_prob": 0.0,
78
+ "mask_time_length": 10,
79
+ "mask_time_min_masks": 2,
80
+ "mask_time_prob": 0.05,
81
+ "model_type": "wav2vec2",
82
+ "num_adapter_layers": 3,
83
+ "num_attention_heads": 16,
84
+ "num_codevector_groups": 2,
85
+ "num_codevectors_per_group": 320,
86
+ "num_conv_pos_embedding_groups": 16,
87
+ "num_conv_pos_embeddings": 128,
88
+ "num_feat_extract_layers": 7,
89
+ "num_hidden_layers": 12,
90
+ "num_negatives": 100,
91
+ "output_hidden_size": 1024,
92
+ "pad_token_id": 0,
93
+ "pooling_mode": "mean",
94
+ "problem_type": "regression",
95
+ "proj_codevector_dim": 768,
96
+ "tdnn_dilation": [
97
+ 1,
98
+ 2,
99
+ 3,
100
+ 1,
101
+ 1
102
+ ],
103
+ "tdnn_dim": [
104
+ 512,
105
+ 512,
106
+ 512,
107
+ 512,
108
+ 1500
109
+ ],
110
+ "tdnn_kernel": [
111
+ 5,
112
+ 3,
113
+ 3,
114
+ 1,
115
+ 1
116
+ ],
117
+ "torch_dtype": "float32",
118
+ "transformers_version": "4.17.0.dev0",
119
+ "use_weighted_layer_sum": false,
120
+ "vocab_size": null,
121
+ "xvector_output_dim": 512
122
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:176d9d1ce29a8bddbab44068b9c1c194c51624c7f1812905e01355da58b18816
3
+ size 661436013