| | |
|---|
| | | 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 |
|---|
| | | |
|---|
| | | # LM Training Stage |
|---|
| | |
|---|
| | | --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} \ |
|---|
| | | --dataset_type $dataset_type \ |
|---|
| | | --resume true \ |
|---|
| | |
|---|
| | | --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}" \ |
|---|
