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-large-cr-ctc-rnnt \
  --use-cr-ctc 1 \
  --use-ctc 1 \
  --use-transducer 1 \
  --use-attention-decoder 0 \
  --num-encoder-layers 2,2,4,5,4,2 \
  --feedforward-dim 512,768,1536,2048,1536,768 \
  --encoder-dim 192,256,512,768,512,256 \
  --encoder-unmasked-dim 192,192,256,320,256,192 \
  --ctc-loss-scale 0.1 \
  --enable-spec-aug 0 \
  --cr-loss-scale 0.02 \
  --time-mask-ratio 2.5 \
  --full-libri 1 \
  --max-duration 1400 \
  --master-port 12343