exp/pretrained_ctc.sh

export CUDA_VISIBLE_DEVICES=7
for m in ctc-decoding attention-decoder-rescoring-no-ngram; do
  ./zipformer/pretrained_ctc.py \
    --use-ctc 1 \
    --use-transducer 0 \
    --use-attention-decoder 1 \
    --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 \
    --checkpoint ./zipformer/exp-large/pretrained.pt \
    --tokens data/lang_bpe_500/tokens.txt \
    --method $m \
    --sample-rate 16000 \
    test_wavs/1089-134686-0001.wav \
    test_wavs/1221-135766-0001.wav \
    test_wavs/1221-135766-0002.wav
done