export CUDA_VISIBLE_DEVICES="0,1,2,3"
./zipformer/train.py \
  --world-size 4 \
  --num-epochs 50 \
  --start-epoch 1 \
  --use-fp16 1 \
  --exp-dir zipformer/exp \
  --causal 0 \
  --max-duration 1000 \
  --master-port 12345