Hugging Face's logo

alefiury
/
wav2vec2-xls-r-300m-pt-br-spontaneous-speech-emotion-recognition

Audio Classification
Transformers
PyTorch
Portuguese
wav2vec2
audio
speech
portuguese-speech-corpus
italian-speech-corpus
english-speech-corpus
arabic-speech-corpus
spontaneous
PyTorch
Inference Endpoints
Model card Files Community
1
alefiury commited on
Commit
840f545
•
1 Parent(s): 8d774c7

add model

Browse files
Files changed (2) hide show
  1. config.json +118 -0
  2. pytorch_model.bin +3 -0
config.json ADDED
@@ -0,0 +1,118 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "./checkpoints/SE_shared_task-xls_r_300m-test-norm_dbfs-01/train",
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
+ "Wav2Vec2ForSequenceClassification"
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": "neutral",
61
+ "1": "non-neutral-female",
62
+ "2": "non-neutral-male"
63
+ },
64
+ "initializer_range": 0.02,
65
+ "intermediate_size": 4096,
66
+ "label2id": {
67
+ "neutral": "0",
68
+ "non-neutral-female": "1",
69
+ "non-neutral-male": "2"
70
+ },
71
+ "layer_norm_eps": 1e-05,
72
+ "layerdrop": 0.1,
73
+ "mask_feature_length": 10,
74
+ "mask_feature_min_masks": 0,
75
+ "mask_feature_prob": 0.0,
76
+ "mask_time_length": 10,
77
+ "mask_time_min_masks": 2,
78
+ "mask_time_prob": 0.075,
79
+ "model_type": "wav2vec2",
80
+ "num_adapter_layers": 3,
81
+ "num_attention_heads": 16,
82
+ "num_codevector_groups": 2,
83
+ "num_codevectors_per_group": 320,
84
+ "num_conv_pos_embedding_groups": 16,
85
+ "num_conv_pos_embeddings": 128,
86
+ "num_feat_extract_layers": 7,
87
+ "num_hidden_layers": 24,
88
+ "num_negatives": 100,
89
+ "output_hidden_size": 1024,
90
+ "pad_token_id": 0,
91
+ "proj_codevector_dim": 768,
92
+ "tdnn_dilation": [
93
+ 1,
94
+ 2,
95
+ 3,
96
+ 1,
97
+ 1
98
+ ],
99
+ "tdnn_dim": [
100
+ 512,
101
+ 512,
102
+ 512,
103
+ 512,
104
+ 1500
105
+ ],
106
+ "tdnn_kernel": [
107
+ 5,
108
+ 3,
109
+ 3,
110
+ 1,
111
+ 1
112
+ ],
113
+ "torch_dtype": "float32",
114
+ "transformers_version": "4.17.0",
115
+ "use_weighted_layer_sum": false,
116
+ "vocab_size": 32,
117
+ "xvector_output_dim": 512
118
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d469c33a3536b2c688f6d0ab50e3685571528adcfcaf2730eb2ef41c5a867767
3
+ size 1262973613