# network architecture
|
# encoder related
|
encoder: e_branchformer
|
encoder_conf:
|
output_size: 512
|
attention_heads: 8
|
attention_layer_type: rel_selfattn
|
pos_enc_layer_type: rel_pos
|
rel_pos_type: latest
|
cgmlp_linear_units: 3072
|
cgmlp_conv_kernel: 31
|
use_linear_after_conv: false
|
gate_activation: identity
|
num_blocks: 17
|
dropout_rate: 0.1
|
positional_dropout_rate: 0.1
|
attention_dropout_rate: 0.1
|
input_layer: conv2d
|
layer_drop_rate: 0.1
|
linear_units: 1024
|
positionwise_layer_type: linear
|
macaron_ffn: true
|
use_ffn: true
|
merge_conv_kernel: 31
|
|
# decoder related
|
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
|
layer_drop_rate: 0.2
|
|
# frontend related
|
frontend: wav_frontend
|
frontend_conf:
|
fs: 16000
|
window: hamming
|
n_mels: 80
|
frame_length: 25
|
frame_shift: 10
|
lfr_m: 1
|
lfr_n: 1
|
|
# hybrid CTC/attention
|
model_conf:
|
ctc_weight: 0.3
|
lsm_weight: 0.1 # label smoothing option
|
length_normalized_loss: false
|
|
# optimization related
|
accum_grad: 2
|
grad_clip: 5
|
max_epoch: 240
|
val_scheduler_criterion:
|
- valid
|
- acc
|
best_model_criterion:
|
- - valid
|
- acc
|
- max
|
keep_nbest_models: 10
|
|
optim: adam
|
optim_conf:
|
lr: 0.002
|
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:
|
data_names: speech,text
|
data_types: sound,text
|
shuffle: True
|
shuffle_conf:
|
shuffle_size: 2048
|
sort_size: 500
|
batch_conf:
|
batch_type: token
|
batch_size: 30000
|
num_workers: 8
|
|
log_interval: 50
|
normalize: None
|
