|
# network architecture
|
model: SanmKWSStreaming
|
model_conf:
|
ctc_weight: 1.0
|
|
# encoder
|
encoder: SANMEncoderChunkOpt
|
encoder_conf:
|
output_size: 256 # dimension of attention
|
attention_heads: 4
|
linear_units: 320 # the number of units of position-wise feed forward
|
num_blocks: 6 # the number of encoder blocks
|
dropout_rate: 0.1
|
positional_dropout_rate: 0.1
|
attention_dropout_rate: 0.1
|
input_layer: pe_online
|
pos_enc_class: SinusoidalPositionEncoder
|
normalize_before: true
|
kernel_size: 11
|
sanm_shift: 0
|
selfattention_layer_type: sanm
|
chunk_size:
|
- 16
|
- 20
|
stride:
|
- 8
|
- 10
|
pad_left:
|
- 4
|
- 5
|
encoder_att_look_back_factor:
|
- 0
|
- 0
|
decoder_att_look_back_factor:
|
- 0
|
- 0
|
|
# frontend related
|
frontend: WavFrontendOnline
|
frontend_conf:
|
fs: 16000
|
window: hamming
|
n_mels: 40
|
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: 100
|
keep_nbest_models: 20
|
avg_nbest_model: 10
|
avg_keep_nbest_models_type: loss
|
validate_interval: 50000
|
save_checkpoint_interval: 50000
|
avg_checkpoint_interval: 1000
|
log_interval: 50
|
|
optim: adam
|
optim_conf:
|
lr: 0.001
|
scheduler: warmuplr
|
scheduler_conf:
|
warmup_steps: 30000
|
|
dataset: AudioDataset
|
dataset_conf:
|
index_ds: IndexDSJsonl
|
batch_sampler: EspnetStyleBatchSampler
|
batch_type: length # example or length
|
batch_size: 64000 # 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: 1600 # filter samples if source_token_len+target_token_len > max_token_length,
|
buffer_size: 2048
|
shuffle: true
|
num_workers: 8
|
preprocessor_speech: SpeechPreprocessSpeedPerturb
|
preprocessor_speech_conf:
|
speed_perturb: [0.9, 1.0, 1.1]
|
|
tokenizer: CharTokenizer
|
tokenizer_conf:
|
unk_symbol: <unk>
|
|
ctc_conf:
|
dropout_rate: 0.0
|
ctc_type: builtin # ctc_type: focalctc, builtin
|
reduce: true
|
ignore_nan_grad: true
|
normalize: null
|
