Update text/cleaners.py

text/cleaners.py

@@ -1,10 +1,6 @@
 import re
 from text.japanese import japanese_to_romaji_with_accent, japanese_to_ipa, japanese_to_ipa2, japanese_to_ipa3
-from text.korean import latin_to_hangul, number_to_hangul, divide_hangul, korean_to_lazy_ipa, korean_to_ipa
-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
-from text.sanskrit import devanagari_to_ipa
-from text.english import english_to_lazy_ipa, english_to_ipa2, english_to_lazy_ipa2
-from text.thai import num_to_thai, latin_to_thai
+
 # from text.shanghainese import shanghainese_to_ipa
 # from text.cantonese import cantonese_to_ipa
 # from text.ngu_dialect import ngu_dialect_to_ipa
@@ -20,89 +16,8 @@ def japanese_cleaners2(text):
     return japanese_cleaners(text).replace('ts', 'ʦ').replace('...', '…')
 
 
-def korean_cleaners(text):
-    '''Pipeline for Korean text'''
-    text = latin_to_hangul(text)
-    text = number_to_hangul(text)
-    text = divide_hangul(text)
-    text = re.sub(r'([\u3131-\u3163])$', r'\1.', text)
-    return text
-
-
-def chinese_cleaners(text):
-    '''Pipeline for Chinese text'''
-    text = number_to_chinese(text)
-    text = chinese_to_bopomofo(text)
-    text = latin_to_bopomofo(text)
-    text = re.sub(r'([ˉˊˇˋ˙])$', r'\1。', text)
-    return text
-
-
-def zh_ja_mixture_cleaners(text):
-    text = re.sub(r'\[ZH\](.*?)\[ZH\]',
-                  lambda x: chinese_to_romaji(x.group(1))+' ', text)
-    text = re.sub(r'\[JA\](.*?)\[JA\]', lambda x: japanese_to_romaji_with_accent(
-        x.group(1)).replace('ts', 'ʦ').replace('u', 'ɯ').replace('...', '…')+' ', text)
-    text = re.sub(r'\s+$', '', text)
-    text = re.sub(r'([^\.,!\?\-…~])$', r'\1.', text)
-    return text
-
-
-def sanskrit_cleaners(text):
-    text = text.replace('॥', '।').replace('ॐ', 'ओम्')
-    text = re.sub(r'([^।])$', r'\1।', text)
-    return text
-
-
-def cjks_cleaners(text):
-    text = re.sub(r'\[ZH\](.*?)\[ZH\]',
-                  lambda x: chinese_to_lazy_ipa(x.group(1))+' ', text)
-    text = re.sub(r'\[JA\](.*?)\[JA\]',
-                  lambda x: japanese_to_ipa(x.group(1))+' ', text)
-    text = re.sub(r'\[KO\](.*?)\[KO\]',
-                  lambda x: korean_to_lazy_ipa(x.group(1))+' ', text)
-    text = re.sub(r'\[SA\](.*?)\[SA\]',
-                  lambda x: devanagari_to_ipa(x.group(1))+' ', text)
-    text = re.sub(r'\[EN\](.*?)\[EN\]',
-                  lambda x: english_to_lazy_ipa(x.group(1))+' ', text)
-    text = re.sub(r'\s+$', '', text)
-    text = re.sub(r'([^\.,!\?\-…~])$', r'\1.', text)
-    return text
-
-
-def cjke_cleaners(text):
-    text = re.sub(r'\[ZH\](.*?)\[ZH\]', lambda x: chinese_to_lazy_ipa(x.group(1)).replace(
-        'ʧ', 'tʃ').replace('ʦ', 'ts').replace('ɥan', 'ɥæn')+' ', text)
-    text = re.sub(r'\[JA\](.*?)\[JA\]', lambda x: japanese_to_ipa(x.group(1)).replace('ʧ', 'tʃ').replace(
-        'ʦ', 'ts').replace('ɥan', 'ɥæn').replace('ʥ', 'dz')+' ', 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)).replace('ɑ', 'a').replace(
-        'ɔ', 'o').replace('ɛ', 'e').replace('ɪ', 'i').replace('ʊ', 'u')+' ', text)
-    text = re.sub(r'\s+$', '', text)
-    text = re.sub(r'([^\.,!\?\-…~])$', r'\1.', text)
-    return text
 
 
-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
-
-
-def thai_cleaners(text):
-    text = num_to_thai(text)
-    text = latin_to_thai(text)
-    return text
-
 
 # def shanghainese_cleaners(text):
 #     text = shanghainese_to_ipa(text)