export CUDA_VISIBLE_DEVICES="0,1,2,3"
# For non-streaming model training:
./zipformer/train.py \
  --world-size 4 \
  --num-epochs 50 \
  --start-epoch 1 \
  --use-fp16 1 \
  --exp-dir zipformer/exp-large \
  --full-libri 1 \
  --use-ctc 1 \
  --use-transducer 0 \
  --use-attention-decoder 1 \
  --ctc-loss-scale 0.1 \
  --attention-decoder-loss-scale 0.9 \
  --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 \
  --max-duration 1200 \
  --master-port 12345