You can not select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
24 lines
421 B
24 lines
421 B
#!/bin/bash
|
|
set -eo pipefail
|
|
|
|
. path.sh
|
|
|
|
stage=0
|
|
stop_stage=100
|
|
has_key=true
|
|
token_type=word
|
|
|
|
. utils/parse_options.sh || exit -1;
|
|
|
|
text=data/text
|
|
|
|
if [ ! -f $text ]; then
|
|
echo "$0: Not find $1";
|
|
exit -1;
|
|
fi
|
|
|
|
if [ $stage -le 0 ] && [ $stop_stage -ge 0 ];then
|
|
echo "text tn & wordseg preprocess"
|
|
rm -rf ${text}.tn
|
|
python3 utils/zh_tn.py --has_key $has_key --token_type $token_type ${text} ${text}.tn
|
|
fi |