update repo

嘉渊

2023-05-16 c568628130ac42ebeea8cf48fe926520a31ff511

 egs/aishell2/paraformerbert/run.sh

@@ -106,8 +106,6 @@
    utils/text2token.py -s 1 -n 1 --space "" ${feats_dir}/data/${train_set}/text | cut -f 2- -d" " | tr " " "\n" \
        | sort | uniq | grep -a -v -e '^\s*$' | awk '{print $0}' >> ${token_list}
    echo "<unk>" >> ${token_list}
    mkdir -p ${feats_dir}/asr_stats_fbank_zh_char/${train_set}
    mkdir -p ${feats_dir}/asr_stats_fbank_zh_char/${valid_set}
 fi

# Training Stage
@@ -117,7 +115,6 @@
    if ! "${skip_extract_embed}"; then
        echo "extract embeddings..."
        local/extract_embeds.sh \
            --bert_model_root ${bert_model_root} \
            --bert_model_name ${bert_model_name} \
            --raw_dataset_path ${feats_dir}
    fi
@@ -134,22 +131,24 @@
            rank=$i
            local_rank=$i
            gpu_id=$(echo $CUDA_VISIBLE_DEVICES | cut -d',' -f$[$i+1])
            asr_train_paraformer.py \
            train.py \
                --task_name asr \
                --gpu_id $gpu_id \
                --use_preprocessor true \
                --dataset_type $dataset_type \
                --token_type $token_type \
                --token_type char \
                --token_list $token_list \
                --train_data_file $feats_dir/$dumpdir/${train_set}/data_bert.list \
                --valid_data_file $feats_dir/$dumpdir/${valid_set}/data_bert.list \
                --data_dir ${feats_dir}/data \
                --train_set ${train_set} \
                --valid_set ${valid_set} \
                --embed_path ${feats_dir}/data \
                --cmvn_file ${feats_dir}/data/${train_set}/cmvn/cmvn.mvn \
                --speed_perturb ${speed_perturb} \
                --dataset_type $dataset_type \
                --resume true \
                --output_dir ${exp_dir}/exp/${model_dir} \
                --config $asr_config \
                --allow_variable_data_keys true \
                --input_size $feats_dim \
                --ngpu $gpu_num \
                --num_worker_count $count \
                --multiprocessing_distributed true \
                --dist_init_method $init_method \
                --dist_world_size $world_size \
                --dist_rank $rank \
@@ -172,7 +171,7 @@
            exit 0
        fi
        mkdir -p "${_logdir}"
        _data="${feats_dir}/${dumpdir}/${dset}"
        _data="${feats_dir}/data/${dset}"
        key_file=${_data}/${scp}
        num_scp_file="$(<${key_file} wc -l)"
        _nj=$([ $inference_nj -le $num_scp_file ] && echo "$inference_nj" || echo "$num_scp_file")
@@ -193,6 +192,7 @@
                --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 \
                --key_file "${_logdir}"/keys.JOB.scp \
                --asr_train_config "${asr_exp}"/config.yaml \
                --asr_model_file "${asr_exp}"/"${inference_asr_model}" \
@@ -213,5 +213,4 @@
        tail -n 3 ${_dir}/text.cer > ${_dir}/text.cer.txt
        cat ${_dir}/text.cer.txt
    done
fi

fi