|
import re |
|
from text.english import english_to_lazy_ipa, english_to_ipa2, english_to_lazy_ipa2 |
|
from text.mandarin import number_to_chinese, chinese_to_bopomofo, latin_to_bopomofo, chinese_to_romaji, chinese_to_lazy_ipa, chinese_to_ipa, chinese_to_ipa2 |
|
|
|
def cjke_cleaners2(text): |
|
text = re.sub(r'\[ZH\](.*?)\[ZH\]', |
|
lambda x: chinese_to_ipa(x.group(1))+' ', text) |
|
text = re.sub(r'\[JA\](.*?)\[JA\]', |
|
lambda x: japanese_to_ipa2(x.group(1))+' ', text) |
|
text = re.sub(r'\[KO\](.*?)\[KO\]', |
|
lambda x: korean_to_ipa(x.group(1))+' ', text) |
|
text = re.sub(r'\[EN\](.*?)\[EN\]', |
|
lambda x: english_to_ipa2(x.group(1))+' ', text) |
|
text = re.sub(r'\s+$', '', text) |
|
text = re.sub(r'([^\.,!\?\-…~])$', r'\1.', text) |
|
return text |