Hugging Face's logo

nguyenvulebinh
/
wav2vec2-base-ja

Automatic Speech Recognition
Transformers
PyTorch
Japanese
wav2vec2
audio
Inference Endpoints
Model card Files Community
wav2vec2-base-ja
File size: 2,384 Bytes 
db3b16e
1e2f9b5
 
db3b16e
 
 
 
 
 
 
1e2f9b5
db3b16e
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1e2f9b5
db3b16e
 
 
 
 
 
1e2f9b5
db3b16e
1e2f9b5
 
db3b16e
1e2f9b5
db3b16e
 
 
 
 
1e2f9b5
 
 
 
 
db3b16e
 
1e2f9b5
db3b16e
 
1e2f9b5
 
db3b16e
1e2f9b5
db3b16e
1e2f9b5
 
db3b16e
 
 
 
 
 
 
 
 
 
1e2f9b5
db3b16e
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1e2f9b5
db3b16e
1e2f9b5
db3b16e
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
 
{
  "_name_or_path": "./model-bin/wav2vec2-csj-ja-base-fb-agment-0.3/checkpoint-87000/",
  "activation_dropout": 0.3,
  "adapter_kernel_size": 3,
  "adapter_stride": 2,
  "add_adapter": false,
  "apply_spec_augment": true,
  "architectures": [
    "Wav2Vec2ForCTC"
  ],
  "attention_dropout": 0.3,
  "bos_token_id": 1,
  "classifier_proj_size": 256,
  "codevector_dim": 256,
  "contrastive_logits_temperature": 0.1,
  "conv_bias": false,
  "conv_dim": [
    512,
    512,
    512,
    512,
    512,
    512,
    512
  ],
  "conv_kernel": [
    10,
    3,
    3,
    3,
    3,
    2,
    2
  ],
  "conv_stride": [
    5,
    2,
    2,
    2,
    2,
    2,
    2
  ],
  "ctc_loss_reduction": "mean",
  "ctc_zero_infinity": false,
  "diversity_loss_weight": 0.1,
  "do_stable_layer_norm": false,
  "eos_token_id": 2,
  "feat_extract_activation": "gelu",
  "feat_extract_norm": "group",
  "feat_proj_dropout": 0.3,
  "feat_quantizer_dropout": 0.0,
  "final_dropout": 0.3,
  "freeze_feat_extract_train": true,
  "hidden_act": "gelu",
  "hidden_dropout": 0.3,
  "hidden_size": 768,
  "initializer_range": 0.02,
  "intermediate_size": 3072,
  "layer_norm_eps": 1e-05,
  "layerdrop": 0.1,
  "mask_channel_length": 10,
  "mask_channel_min_space": 1,
  "mask_channel_other": 0.0,
  "mask_channel_prob": 0.0,
  "mask_channel_selection": "static",
  "mask_feature_length": 10,
  "mask_feature_min_masks": 0,
  "mask_feature_prob": 0,
  "mask_time_length": 10,
  "mask_time_min_masks": 2,
  "mask_time_min_space": 1,
  "mask_time_other": 0.0,
  "mask_time_prob": 0.05,
  "mask_time_selection": "static",
  "model_type": "wav2vec2",
  "no_mask_channel_overlap": false,
  "no_mask_time_overlap": false,
  "num_adapter_layers": 3,
  "num_attention_heads": 12,
  "num_codevector_groups": 2,
  "num_codevectors_per_group": 320,
  "num_conv_pos_embedding_groups": 16,
  "num_conv_pos_embeddings": 128,
  "num_feat_extract_layers": 7,
  "num_hidden_layers": 12,
  "num_negatives": 100,
  "output_hidden_size": 768,
  "pad_token_id": 2278,
  "proj_codevector_dim": 256,
  "tdnn_dilation": [
    1,
    2,
    3,
    1,
    1
  ],
  "tdnn_dim": [
    512,
    512,
    512,
    512,
    1500
  ],
  "tdnn_kernel": [
    5,
    3,
    3,
    1,
    1
  ],
  "torch_dtype": "float32",
  "transformers_version": "4.23.1",
  "use_weighted_layer_sum": false,
  "vocab_size": 2279,
  "xvector_output_dim": 512
}