diff --git a/egs/aishell2/paraformerbert/local/extract_embeds.sh b/egs/aishell2/paraformerbert/local/extract_embeds.sh index 049d38cb8..d3cbc4bdb 100755 --- a/egs/aishell2/paraformerbert/local/extract_embeds.sh +++ b/egs/aishell2/paraformerbert/local/extract_embeds.sh @@ -11,7 +11,7 @@ model_path=${bert_model_name} nj=32 -for data_set in train dev test;do +for data_set in train dev_ios test;do scp=$raw_dataset_path/data/${data_set}/text local_scp_dir_raw=${raw_dataset_path}/data/embeds/${data_set} local_scp_dir=$local_scp_dir_raw/split$nj diff --git a/egs/aishell2/paraformerbert/run.sh b/egs/aishell2/paraformerbert/run.sh index ef74dd144..2fba30d55 100755 --- a/egs/aishell2/paraformerbert/run.sh +++ b/egs/aishell2/paraformerbert/run.sh @@ -173,7 +173,7 @@ if [ ${stage} -le 4 ] && [ ${stop_stage} -ge 4 ]; then exit 0 fi mkdir -p "${_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") @@ -194,6 +194,7 @@ if [ ${stage} -le 4 ] && [ ${stop_stage} -ge 4 ]; then --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}" \