| | |
|---|
| | | token_type=char |
|---|
| | | scp=wav.scp |
|---|
| | | type=sound |
|---|
| | | stage=1 |
|---|
| | | stage=2 |
|---|
| | | stop_stage=3 |
|---|
| | | |
|---|
| | | # feature configuration |
|---|
| | |
|---|
| | | data_url=www.openslr.org/resources/33 |
|---|
| | | |
|---|
| | | # exp tag |
|---|
| | | tag="" |
|---|
| | | tag="exp1" |
|---|
| | | |
|---|
| | | . utils/parse_options.sh || exit 1; |
|---|
| | | |
|---|
| | |
|---|
| | | echo "<blank>" > ${token_list} |
|---|
| | | echo "<s>" >> ${token_list} |
|---|
| | | echo "</s>" >> ${token_list} |
|---|
| | | utils/text2token.py -s 1 -n 1 --space "" ${feats_dir}/data/train/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} |
|---|
| | | echo "<unk>" >> ${token_list} |
|---|
| | | fi |
|---|
