| | |
|---|
| | | 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 |
|---|
| | |
|---|
| | | echo "extract embeddings..." |
|---|
| | | local/extract_embeds.sh \ |
|---|
| | | --bert_model_name ${bert_model_name} \ |
|---|
| | | --raw_dataset_path ${feats_dir} |
|---|
| | | --raw_dataset_path ${feats_dir} \ |
|---|
| | | --nj $nj |
|---|
| | | fi |
|---|
| | | mkdir -p ${exp_dir}/exp/${model_dir} |
|---|
| | | mkdir -p ${exp_dir}/exp/${model_dir}/log |
|---|
