# pylint: disable=unnecessary-comprehension
# Mappings from symbol to numeric ID and vice versa:
_symbol_to_id = {s: i for i, s in enumerate(symbols)}
_id_to_symbol = {i: s for i, s in enumerate(symbols)}
_phonemes_to_id = {s: i for i, s in enumerate(phonemes)}
_id_to_phonemes = {i: s for i, s in enumerate(phonemes)}
_symbols = symbols
_phonemes = phonemes
# Regular expression matching text enclosed in curly braces:
_CURLY_RE = re.compile(r"(.*?)\{(.+?)\}(.*)")
# Regular expression matching punctuations, ignoring empty space
PHONEME_PUNCTUATION_PATTERN = r"[" + _punctuations.replace(" ", "") + "]+"
# Table for str.translate to fix gruut/TTS phoneme mismatch
GRUUT_TRANS_TABLE = str.maketrans("g", "ɡ")
def text2phone(text, language, use_espeak_phonemes=False):
"""Convert graphemes to phonemes.
Parameters:
text (str): text to phonemize
language (str): language of the text
Returns:
ph (str): phonemes as a string seperated by "|"
ph = "ɪ|g|ˈ|z|æ|m|p|ə|l"
"""
# pylint: disable=unnecessary-comprehension
# Mappings from symbol to numeric ID and vice versa:
_symbol_to_id = {s: i for i, s in enumerate(symbols)}
_id_to_symbol = {i: s for i, s in enumerate(symbols)}
_phonemes_to_id = {s: i for i, s in enumerate(phonemes)}
_id_to_phonemes = {i: s for i, s in enumerate(phonemes)}
_symbols = symbols
_phonemes = phonemes
# Regular expression matching text enclosed in curly braces:
_CURLY_RE = re.compile(r'(.*?)\{(.+?)\}(.*)')
# Regular expression matching punctuations, ignoring empty space
PHONEME_PUNCTUATION_PATTERN = r'[' + _punctuations.replace(' ', '') + ']+'
def text2phone(text, language):
'''Convert graphemes to phonemes. For most of the languages, it calls
the phonemizer python library that calls espeak/espeak-ng. For chinese
mandarin, it calls pypinyin + custom function for phonemizing
Parameters:
text (str): text to phonemize
language (str): language of the text
Returns:
ph (str): phonemes as a string seperated by "|"
ph = "ɪ|g|ˈ|z|æ|m|p|ə|l"
'''
# TO REVIEW : How to have a good implementation for this?