File size: 2,509 Bytes
b0e99c8
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
119
120
121
122
123
124

# network architecture
model: Paraformer
model_conf:
    ctc_weight: 0.0
    lsm_weight: 0.1
    length_normalized_loss: true
    predictor_weight: 1.0
    predictor_bias: 1
    sampling_ratio: 0.75

# encoder
encoder: SANMEncoder
encoder_conf:
    output_size: 512
    attention_heads: 4
    linear_units: 2048
    num_blocks: 50
    dropout_rate: 0.1
    positional_dropout_rate: 0.1
    attention_dropout_rate: 0.1
    input_layer: pe
    pos_enc_class: SinusoidalPositionEncoder
    normalize_before: true
    kernel_size: 11
    sanm_shfit: 0
    selfattention_layer_type: sanm

# decoder
decoder: ParaformerSANMDecoder
decoder_conf:
    attention_heads: 4
    linear_units: 2048
    num_blocks: 16
    dropout_rate: 0.1
    positional_dropout_rate: 0.1
    self_attention_dropout_rate: 0.1
    src_attention_dropout_rate: 0.1
    att_layer_num: 16
    kernel_size: 11
    sanm_shfit: 0

predictor: CifPredictorV2
predictor_conf:
    idim: 512
    threshold: 1.0
    l_order: 1
    r_order: 1
    tail_threshold: 0.45

# frontend related
frontend: WavFrontend
frontend_conf:
    fs: 16000
    window: hamming
    n_mels: 80
    frame_length: 25
    frame_shift: 10
    lfr_m: 7
    lfr_n: 6

specaug: SpecAugLFR
specaug_conf:
    apply_time_warp: false
    time_warp_window: 5
    time_warp_mode: bicubic
    apply_freq_mask: true
    freq_mask_width_range:
    - 0
    - 30
    lfr_rate: 6
    num_freq_mask: 1
    apply_time_mask: true
    time_mask_width_range:
    - 0
    - 12
    num_time_mask: 1

train_conf:
  accum_grad: 1
  grad_clip: 5
  max_epoch: 150
  val_scheduler_criterion:
      - valid
      - acc
  best_model_criterion:
  -   - valid
      - acc
      - max
  keep_nbest_models: 10
  log_interval: 50

optim: adam
optim_conf:
   lr: 0.0005
scheduler: warmuplr
scheduler_conf:
   warmup_steps: 30000

dataset: AudioDataset
dataset_conf:
    index_ds: IndexDSJsonl
    batch_sampler: DynamicBatchLocalShuffleSampler
    batch_type: example # example or length
    batch_size: 1 # if batch_type is example, batch_size is the numbers of samples; if length, batch_size is source_token_len+target_token_len;
    max_token_length: 2048 # filter samples if source_token_len+target_token_len > max_token_length, 
    buffer_size: 500
    shuffle: True
    num_workers: 0

tokenizer: CharTokenizer
tokenizer_conf:
  unk_symbol: <unk>
  split_with_space: true
  

input_size: 560
ctc_conf:
    dropout_rate: 0.0
    ctc_type: builtin
    reduce: true
    ignore_nan_grad: true
normalize: null