Hugging Face's logo

khanhld
/
wav2vec2-base-vietnamese-160h

Automatic Speech Recognition
Transformers
PyTorch
Vietnamese
wav2vec2
audio
speech
Transformer
vietnamese
Eval Results
Inference Endpoints
Model card Files
khanhld commited on
Commit
d5e71f1
•
1 Parent(s): dc1a950

upload model

Browse files
Files changed (1) hide show
  1. config.json +118 -0
config.json ADDED
@@ -0,0 +1,118 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "facebook/wav2vec2-base",
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
+ "Wav2Vec2ForCTC"
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": false,
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": false,
46
+ "diversity_loss_weight": 0.1,
47
+ "do_stable_layer_norm": false,
48
+ "eos_token_id": 2,
49
+ "feat_extract_activation": "gelu",
50
+ "feat_extract_norm": "group",
51
+ "feat_proj_dropout": 0.1,
52
+ "feat_quantizer_dropout": 0.0,
53
+ "final_dropout": 0.0,
54
+ "freeze_feat_extract_train": true,
55
+ "gradient_checkpointing": false,
56
+ "hidden_act": "gelu",
57
+ "hidden_dropout": 0.1,
58
+ "hidden_size": 768,
59
+ "initializer_range": 0.02,
60
+ "intermediate_size": 3072,
61
+ "layer_norm_eps": 1e-05,
62
+ "layerdrop": 0.0,
63
+ "mask_channel_length": 10,
64
+ "mask_channel_min_space": 1,
65
+ "mask_channel_other": 0.0,
66
+ "mask_channel_prob": 0.0,
67
+ "mask_channel_selection": "static",
68
+ "mask_feature_length": 10,
69
+ "mask_feature_min_masks": 0,
70
+ "mask_feature_prob": 0.0,
71
+ "mask_time_length": 10,
72
+ "mask_time_min_masks": 2,
73
+ "mask_time_min_space": 1,
74
+ "mask_time_other": 0.0,
75
+ "mask_time_prob": 0.05,
76
+ "mask_time_selection": "static",
77
+ "model_type": "wav2vec2",
78
+ "no_mask_channel_overlap": false,
79
+ "no_mask_time_overlap": false,
80
+ "num_adapter_layers": 3,
81
+ "num_attention_heads": 12,
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": 12,
88
+ "num_negatives": 100,
89
+ "output_hidden_size": 768,
90
+ "pad_token_id": 95,
91
+ "proj_codevector_dim": 256,
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": "4.18.0",
115
+ "use_weighted_layer_sum": false,
116
+ "vocab_size": 96,
117
+ "xvector_output_dim": 512
118
+ }