Merge pull request #552 from alibaba-damo-academy/dev_wjm2

hnluo

2023-05-25 e0a8c4b00631ed636418f4280964e473f05d5002

 egs/aishell/conformer/run.sh

@@ -85,7 +85,7 @@

if [ ${stage} -le 1 ] && [ ${stop_stage} -ge 1 ]; then
    echo "stage 1: Feature and CMVN Generation"
    utils/compute_cmvn.sh --cmd "$train_cmd" --nj $nj --feats_dim ${feats_dim} ${feats_dir}/data/${train_set}
    utils/compute_cmvn.sh ${feats_dir}/data/${train_set} --cmd "$train_cmd" --nj $nj --feats_dim ${feats_dim} --config $asr_config --scale 1.0
fi

token_list=${feats_dir}/data/${lang}_token_list/char/tokens.txt
@@ -136,7 +136,7 @@
                --train_set ${train_set} \
                --valid_set ${valid_set} \
                --data_file_names "wav.scp,text" \
                --cmvn_file ${feats_dir}/data/${train_set}/cmvn/cmvn.mvn \
                --cmvn_file ${feats_dir}/data/${train_set}/cmvn/am.mvn \
                --speed_perturb ${speed_perturb} \
                --resume true \
                --output_dir ${exp_dir}/exp/${model_dir} \
@@ -186,7 +186,7 @@
                --njob ${njob} \
                --gpuid_list ${gpuid_list} \
                --data_path_and_name_and_type "${_data}/${scp},speech,${type}" \
                --cmvn_file ${feats_dir}/data/${train_set}/cmvn/cmvn.mvn \
                --cmvn_file ${feats_dir}/data/${train_set}/cmvn/am.mvn \
                --key_file "${_logdir}"/keys.JOB.scp \
                --asr_train_config "${asr_exp}"/config.yaml \
                --asr_model_file "${asr_exp}"/"${inference_asr_model}" \
@@ -207,4 +207,19 @@
        tail -n 3 ${_dir}/text.cer > ${_dir}/text.cer.txt
        cat ${_dir}/text.cer.txt
    done
fi

# Prepare files for ModelScope fine-tuning and inference
if [ ${stage} -le 6 ] && [ ${stop_stage} -ge 6 ]; then
    echo "stage 6: ModelScope Preparation"
    cp ${feats_dir}/data/${train_set}/cmvn/am.mvn ${exp_dir}/exp/${model_dir}/am.mvn
    vocab_size=$(cat ${token_list} | wc -l)
    python utils/gen_modelscope_configuration.py \
        --am_model_name $inference_asr_model \
        --mode asr \
        --model_name conformer \
        --dataset aishell \
        --output_dir $exp_dir/exp/$model_dir \
        --vocab_size $vocab_size \
        --tag $tag
fi