嘉渊
2023-07-05 a43b3da4be856f61f3285e21c3b28cf25a9d4e7c
egs/aishell/branchformer/conf/train_asr_branchformer.yaml
@@ -34,20 +34,27 @@
    self_attention_dropout_rate: 0.
    src_attention_dropout_rate: 0.
# 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
# minibatch related
batch_type: numel
batch_bins: 25000000
# optimization related
accum_grad: 1
grad_clip: 5
max_epoch: 60
max_epoch: 180
val_scheduler_criterion:
    - valid
    - acc
@@ -65,10 +72,6 @@
scheduler_conf:
   warmup_steps: 35000
num_workers: 4      # num of workers of data loader
use_amp: true      # automatic mixed precision
unused_parameters: false    # set as true if some params are unused in DDP
specaug: specaug
specaug_conf:
    apply_time_warp: true
@@ -84,3 +87,18 @@
    - 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: 25000
    num_workers: 8
log_interval: 50
normalize: None