PaddleSpeech/examples/ted_en_zh/st1/local/train.sh

#!/bin/bash

if [ $# -lt 3 ] && [ $# -gt 4 ];then
    echo "usage: CUDA_VISIBLE_DEVICES=0 ${0} config_path ckpt_name ips(optional)"
    exit -1
fi

ngpu=$(echo $CUDA_VISIBLE_DEVICES | awk -F "," '{print NF}')
echo "using $ngpu gpus..."

config_path=$1
ckpt_name=$2
ckpt_path=$3
ips=$3

if [ ! $ips ];then
  ips_config=
else
  ips_config="--ips="${ips}
fi

mkdir -p exp

mkdir -p exp

# seed may break model convergence
seed=0
if [ ${seed} != 0 ]; then
    export FLAGS_cudnn_deterministic=True
fi

if [ ${ngpu} == 0 ]; then
python3 -u ${BIN_DIR}/train.py \
--ngpu ${ngpu} \
--config ${config_path} \
--output exp/${ckpt_name} \
--checkpoint_path "${ckpt_path}" \
--seed ${seed}
else
python3 -m paddle.distributed.launch --gpus=${CUDA_VISIBLE_DEVICES} ${ips_config} ${BIN_DIR}/train.py \
--ngpu ${ngpu} \
--config ${config_path} \
--output exp/${ckpt_name} \
--checkpoint_path "${ckpt_path}" \
--seed ${seed}
fi

if [ ${seed} != 0 ]; then
    unset FLAGS_cudnn_deterministic
fi

if [ $? -ne 0 ]; then
    echo "Failed in training!"
    exit 1
fi

exit 0