File size: 1,707 Bytes
d80265b
205bf6c
 
d80265b
 
205bf6c
d80265b
205bf6c
 
 
 
d80265b
 
205bf6c
d80265b
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
205bf6c
d80265b
205bf6c
d80265b
 
a8c22c7
205bf6c
 
 
 
 
a8c22c7
d80265b
205bf6c
 
 
d80265b
205bf6c
d80265b
205bf6c
d80265b
 
 
 
 
 
205bf6c
 
d80265b
 
 
205bf6c
 
 
d80265b
 
 
205bf6c
d80265b
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
{
  "_name_or_path": "team-lucid/hubert-base-korean",
  "activation_dropout": 0.1,
  "apply_spec_augment": true,
  "architectures": [
    "HubertForCTC"
  ],
  "attention_dropout": 0.1,
  "auto_map": {
    "FlaxAutoModel": "team-lucid/hubert-base-korean--modeling_flax_hubert.FlaxHubertModel"
  },
  "bos_token_id": 1,
  "classifier_proj_size": 256,
  "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": "sum",
  "ctc_zero_infinity": false,
  "do_stable_layer_norm": false,
  "eos_token_id": 2,
  "feat_extract_activation": "gelu",
  "feat_extract_dropout": 0.0,
  "feat_extract_norm": "group",
  "feat_proj_dropout": 0.1,
  "feat_proj_layer_norm": true,
  "final_dropout": 0.1,
  "final_proj_size": 256,
  "gradient_checkpointing": false,
  "hidden_act": "gelu",
  "hidden_dropout": 0.1,
  "hidden_dropout_prob": 0.1,
  "hidden_size": 768,
  "initializer_range": 0.02,
  "intermediate_size": 3072,
  "layer_norm_eps": 1e-05,
  "layerdrop": 0.1,
  "mask_feature_length": 10,
  "mask_feature_min_masks": 0,
  "mask_feature_prob": 0.0,
  "mask_time_length": 10,
  "mask_time_min_masks": 2,
  "mask_time_prob": 0.05,
  "model_type": "hubert",
  "num_attention_heads": 12,
  "num_conv_pos_embedding_groups": 16,
  "num_conv_pos_embeddings": 128,
  "num_feat_extract_layers": 7,
  "num_hidden_layers": 12,
  "pad_token_id": 0,
  "tokenizer_class": "Wav2Vec2CTCTokenizer",
  "torch_dtype": "float32",
  "transformers_version": "4.44.2",
  "use_weighted_layer_sum": false,
  "vocab_size": 53
}