text/cleaners.py

from viphoneme import vi2IPA
import re

_whitespace_re = re.compile(r'\s+')


def lowercase(text):
  return text.lower()

def collapse_whitespace(text):
  return re.sub(_whitespace_re, ' ', text)

def vietnamese_cleaner(text):
    print(text,'test1')
    text = lowercase(text) # PL_BERT_CASE
    phonemes = vi2IPA(text)
    phonemes = collapse_whitespace(phonemes)
    return phonemes

# import MeCab
# import pykakasi

# mc = MeCab.Tagger("-Owakati")
# kks = pykakasi.kakasi()

# # define function to convert text to phonemes
# def japanese_to_phonemes(text):
#     # convert text to hiragana
#     result = kks.convert(text)
#     hiragana = ''.join([item['hira'] for item in result])

#     # convert hiragana to katakana
#     katakana = kks.convert(hiragana)
#     katakana = ''.join([item['kana'] for item in katakana])

#     # convert katakana to romaji (phonemes)
#     romaji = kks.convert(katakana)
#     romaji = ''.join([item['hepburn'] for item in romaji])

#     return romaji

# def japanese_cleaner(text):
#     cleaned_text = mc.parse(text)
#     phonemes = japanese_to_phonemes(cleaned_text)
#     return phonemes