Update modelscope_models.md

Chong Zhang

2023-05-23 5fec3c9e58fceda85fa2daf7deec2492372dac8a

 egs/aishell2/conformer/run.sh

@@ -9,7 +9,7 @@
gpu_inference=true  # Whether to perform gpu decoding, set false for cpu decoding
# for gpu decoding, inference_nj=ngpu*njob; for cpu decoding, inference_nj=njob
njob=5
train_cmd=tools/run.pl
train_cmd=utils/run.pl
infer_cmd=utils/run.pl

# general configuration
@@ -20,16 +20,17 @@
type=sound
scp=wav.scp
speed_perturb="0.9 1.0 1.1"
stage=1
stop_stage=1
dataset_type=large
stage=0
stop_stage=5

# feature configuration
feats_dim=80
nj=64

# data
tr_dir=/nfs/wangjiaming.wjm/asr_data/aishell2/AISHELL-2/iOS/data
dev_tst_dir=/nfs/wangjiaming.wjm/asr_data/aishell2/AISHELL-DEV-TEST-SET
tr_dir=
dev_tst_dir=

# exp tag
tag="exp1"
@@ -99,23 +100,21 @@
    echo "<blank>" > ${token_list}
    echo "<s>" >> ${token_list}
    echo "</s>" >> ${token_list}
    tools/text2token.py -s 1 -n 1 --space "" ${feats_dir}/data/${train_set}/text | cut -f 2- -d" " | tr " " "\n" \
    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}' >> ${token_list}
    num_token=$(cat ${token_list} | wc -l)
    echo "<unk>" >> ${token_list}
    vocab_size=$(cat ${token_list} | wc -l)
    awk -v v=,${vocab_size} '{print $0v}' ${feat_train_dir}/text_shape > ${feat_train_dir}/text_shape.char
    awk -v v=,${vocab_size} '{print $0v}' ${feat_dev_dir}/text_shape > ${feat_dev_dir}/text_shape.char
    mkdir -p ${feats_dir}/asr_stats_fbank_zh_char/${train_set}
    mkdir -p ${feats_dir}/asr_stats_fbank_zh_char/${valid_set}
    cp ${feat_train_dir}/speech_shape ${feat_train_dir}/text_shape ${feat_train_dir}/text_shape.char ${feats_dir}/asr_stats_fbank_zh_char/${train_set} 
    cp ${feat_dev_dir}/speech_shape ${feat_dev_dir}/text_shape ${feat_dev_dir}/text_shape.char ${feats_dir}/asr_stats_fbank_zh_char/${valid_set}
fi
 fi

# Training Stage
# LM Training Stage
world_size=$gpu_num  # run on one machine
if [ ${stage} -le 3 ] && [ ${stop_stage} -ge 3 ]; then
    echo "stage 3: Training"
    echo "stage 3: LM Training"
fi

# ASR Training Stage
world_size=$gpu_num  # run on one machine
if [ ${stage} -le 4 ] && [ ${stop_stage} -ge 4 ]; then
    echo "stage 4: ASR Training"
    mkdir -p ${exp_dir}/exp/${model_dir}
    mkdir -p ${exp_dir}/exp/${model_dir}/log
    INIT_FILE=${exp_dir}/exp/${model_dir}/ddp_init
@@ -129,21 +128,24 @@
            rank=$i
            local_rank=$i
            gpu_id=$(echo $CUDA_VISIBLE_DEVICES | cut -d',' -f$[$i+1])
            asr_train.py \
            train.py \
                --task_name asr \
                --gpu_id $gpu_id \
                --use_preprocessor true \
                --dataset_type $dataset_type \
                --token_type char \
                --token_list $token_list \
                --train_data_file $feats_dir/$dumpdir/${train_set}/data.list \
                --valid_data_file $feats_dir/$dumpdir/${valid_set}/data.list \
                --data_dir ${feats_dir}/data \
                --train_set ${train_set} \
                --valid_set ${valid_set} \
                --data_file_names "wav.scp,text" \
                --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 \
                --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 \
@@ -154,8 +156,8 @@
fi

# Testing Stage
if [ ${stage} -le 4 ] && [ ${stop_stage} -ge 4 ]; then
    echo "stage 4: Inference"
if [ ${stage} -le 5 ] && [ ${stop_stage} -ge 5 ]; then
    echo "stage 5: Inference"
    for dset in ${test_sets}; do
        asr_exp=${exp_dir}/exp/${model_dir}
        inference_tag="$(basename "${inference_config}" .yaml)"
@@ -166,7 +168,7 @@
            exit 0
        fi
        mkdir -p "${_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")
@@ -187,6 +189,7 @@
                --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}" \