Hugging Face's logo

handsonbrain
/
audio-to-texto-pt-br

ONNX
wav2vec2
Model card Files Community
handsonbrain commited on
Commit
ddd55e0
•
1 Parent(s): 8aa5921

Upload 3 files

Browse files
Files changed (3) hide show
  1. config.json +118 -0
  2. model.onnx +3 -0
  3. preprocessor_config.json +9 -0
config.json ADDED
@@ -0,0 +1,118 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "alefiury/wav2vec2-xls-r-300m-pt-br-spontaneous-speech-emotion-recognition",
3
+ "activation_dropout": 0.0,
4
+ "adapter_attn_dim": null,
5
+ "adapter_kernel_size": 3,
6
+ "adapter_stride": 2,
7
+ "add_adapter": false,
8
+ "apply_spec_augment": true,
9
+ "architectures": [
10
+ "Wav2Vec2ForSequenceClassification"
11
+ ],
12
+ "attention_dropout": 0.1,
13
+ "bos_token_id": 1,
14
+ "classifier_proj_size": 256,
15
+ "codevector_dim": 768,
16
+ "contrastive_logits_temperature": 0.1,
17
+ "conv_bias": true,
18
+ "conv_dim": [
19
+ 512,
20
+ 512,
21
+ 512,
22
+ 512,
23
+ 512,
24
+ 512,
25
+ 512
26
+ ],
27
+ "conv_kernel": [
28
+ 10,
29
+ 3,
30
+ 3,
31
+ 3,
32
+ 3,
33
+ 2,
34
+ 2
35
+ ],
36
+ "conv_stride": [
37
+ 5,
38
+ 2,
39
+ 2,
40
+ 2,
41
+ 2,
42
+ 2,
43
+ 2
44
+ ],
45
+ "ctc_loss_reduction": "sum",
46
+ "ctc_zero_infinity": false,
47
+ "diversity_loss_weight": 0.1,
48
+ "do_stable_layer_norm": true,
49
+ "eos_token_id": 2,
50
+ "feat_extract_activation": "gelu",
51
+ "feat_extract_dropout": 0.0,
52
+ "feat_extract_norm": "layer",
53
+ "feat_proj_dropout": 0.1,
54
+ "feat_quantizer_dropout": 0.0,
55
+ "final_dropout": 0.0,
56
+ "gradient_checkpointing": false,
57
+ "hidden_act": "gelu",
58
+ "hidden_dropout": 0.1,
59
+ "hidden_size": 1024,
60
+ "id2label": {
61
+ "0": "neutral",
62
+ "1": "non-neutral-female",
63
+ "2": "non-neutral-male"
64
+ },
65
+ "initializer_range": 0.02,
66
+ "intermediate_size": 4096,
67
+ "label2id": {
68
+ "neutral": "0",
69
+ "non-neutral-female": "1",
70
+ "non-neutral-male": "2"
71
+ },
72
+ "layer_norm_eps": 1e-05,
73
+ "layerdrop": 0.1,
74
+ "mask_feature_length": 10,
75
+ "mask_feature_min_masks": 0,
76
+ "mask_feature_prob": 0.0,
77
+ "mask_time_length": 10,
78
+ "mask_time_min_masks": 2,
79
+ "mask_time_prob": 0.075,
80
+ "model_type": "wav2vec2",
81
+ "num_adapter_layers": 3,
82
+ "num_attention_heads": 16,
83
+ "num_codevector_groups": 2,
84
+ "num_codevectors_per_group": 320,
85
+ "num_conv_pos_embedding_groups": 16,
86
+ "num_conv_pos_embeddings": 128,
87
+ "num_feat_extract_layers": 7,
88
+ "num_hidden_layers": 24,
89
+ "num_negatives": 100,
90
+ "output_hidden_size": 1024,
91
+ "pad_token_id": 0,
92
+ "proj_codevector_dim": 768,
93
+ "tdnn_dilation": [
94
+ 1,
95
+ 2,
96
+ 3,
97
+ 1,
98
+ 1
99
+ ],
100
+ "tdnn_dim": [
101
+ 512,
102
+ 512,
103
+ 512,
104
+ 512,
105
+ 1500
106
+ ],
107
+ "tdnn_kernel": [
108
+ 5,
109
+ 3,
110
+ 3,
111
+ 1,
112
+ 1
113
+ ],
114
+ "transformers_version": "4.42.4",
115
+ "use_weighted_layer_sum": false,
116
+ "vocab_size": 32,
117
+ "xvector_output_dim": 512
118
+ }
model.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:76ed56e508a1bf1bc434973c3f58de184ea42f1a19b1a422a29026c11f437be1
3
+ size 1263347663
preprocessor_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_normalize": true,
3
+ "feature_extractor_type": "Wav2Vec2FeatureExtractor",
4
+ "feature_size": 1,
5
+ "padding_side": "right",
6
+ "padding_value": 0,
7
+ "return_attention_mask": true,
8
+ "sampling_rate": 16000
9
+ }