exp/train.sh

export CUDA_VISIBLE_DEVICES="0,1"
# for non-streaming model training:
./zipformer/train.py \
  --world-size 2 \
  --num-epochs 50 \
  --start-epoch 1 \
  --use-fp16 1 \
  --exp-dir zipformer/exp-small/ \
  --use-cr-ctc 1 \
  --use-ctc 1 \
  --use-transducer 0 \
  --use-attention-decoder 0 \
  --num-encoder-layers 2,2,2,2,2,2 \
  --feedforward-dim 512,768,768,768,768,768 \
  --encoder-dim 192,256,256,256,256,256 \
  --encoder-unmasked-dim 192,192,192,192,192,192 \
  --base-lr 0.04 \
  --enable-spec-aug 0 \
  --cr-loss-scale 0.2 \
  --time-mask-ratio 2.5 \
  --full-libri 1 \
  --max-duration 850 \
  --master-port 12348