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
| encoder: conformer
| encoder_conf:
| output_size: 512
| attention_heads: 8
| linear_units: 2048
| num_blocks: 12
| dropout_rate: 0.1
| positional_dropout_rate: 0.1
| attention_dropout_rate: 0.1
| input_layer: conv2d
| normalize_before: true
| macaron_style: true
| rel_pos_type: latest
| pos_enc_layer_type: rel_pos
| selfattention_layer_type: rel_selfattn
| activation_type: swish
| use_cnn_module: true
| cnn_module_kernel: 31
|
| decoder: transformer
| decoder_conf:
| attention_heads: 8
| linear_units: 2048
| num_blocks: 6
| dropout_rate: 0.1
| positional_dropout_rate: 0.1
| self_attention_dropout_rate: 0.1
| src_attention_dropout_rate: 0.1
|
| model_conf:
| ctc_weight: 0.3
| lsm_weight: 0.1
| length_normalized_loss: false
|
| accum_grad: 2
| max_epoch: 50
| patience: none
| init: none
| best_model_criterion:
| - - valid
| - acc
| - max
| keep_nbest_models: 10
|
| optim: adam
| optim_conf:
| lr: 0.0025
| weight_decay: 0.000001
| scheduler: warmuplr
| scheduler_conf:
| warmup_steps: 40000
|
| specaug: specaug
| specaug_conf:
| apply_time_warp: true
| time_warp_window: 5
| time_warp_mode: bicubic
| apply_freq_mask: true
| freq_mask_width_range:
| - 0
| - 27
| num_freq_mask: 2
| apply_time_mask: true
| time_mask_width_ratio_range:
| - 0.
| - 0.05
| num_time_mask: 10
|
| dataset_conf:
| shuffle: True
| shuffle_conf:
| shuffle_size: 1024
| sort_size: 500
| batch_conf:
| batch_type: token
| batch_size: 10000
| num_workers: 8
|
| log_interval: 50
| normalize: utterance_mvn
|
|
