1
{
2
  "speechbrain_interface": "EncoderDecoderASR",
3
  "activation_dropout": 0.1,
4
  "apply_spec_augment": true,
5
  "architectures": [
6
    "Wav2Vec2Model"
7
  ],
8
  "attention_dropout": 0.1,
9
  "bos_token_id": 1,
10
  "conv_bias": true,
11
  "conv_dim": [
12
    512,
13
    512,
14
    512,
15
    512,
16
    512,
17
    512,
18
    512
19
  ],
20
  "conv_kernel": [
21
    10,
22
    3,
23
    3,
24
    3,
25
    3,
26
    2,
27
    2
28
  ],
29
  "conv_stride": [
30
    5,
31
    2,
32
    2,
33
    2,
34
    2,
35
    2,
36
    2
37
  ],
38
  "ctc_loss_reduction": "sum",
39
  "ctc_zero_infinity": false,
40
  "do_stable_layer_norm": true,
41
  "eos_token_id": 2,
42
  "feat_extract_activation": "gelu",
43
  "feat_extract_dropout": 0.0,
44
  "feat_extract_norm": "layer",
45
  "feat_proj_dropout": 0.1,
46
  "final_dropout": 0.1,
47
  "gradient_checkpointing": false,
48
  "hidden_act": "gelu",
49
  "hidden_dropout": 0.1,
50
  "hidden_dropout_prob": 0.1,
51
  "hidden_size": 1024,
52
  "initializer_range": 0.02,
53
  "intermediate_size": 4096,
54
  "layer_norm_eps": 1e-05,
55
  "layerdrop": 0.1,
56
  "mask_feature_length": 10,
57
  "mask_feature_prob": 0.0,
58
  "mask_time_length": 10,
59
  "mask_time_prob": 0.05,
60
  "model_type": "wav2vec2",
61
  "num_attention_heads": 16,
62
  "num_conv_pos_embedding_groups": 16,
63
  "num_conv_pos_embeddings": 128,
64
  "num_feat_extract_layers": 7,
65
  "num_hidden_layers": 24,
66
  "pad_token_id": 0,
67
  "transformers_version": "4.4.0.dev0",
68
  "vocab_size": 32
69
}