""" from https://github.com/keithito/tacotron """

'''
Defines the set of symbols used in text input to the model.
'''

# Original
# _pad        = '_'
# _punctuation = '[]\'* '
# _letters = 'aảáăặấbcdđefghijklmnoóôớờprstuúữvwxyz'  
# _letters_ipa = "ɑæɔʤəɛɪɯŋɲʂʃʈʧʊɣɤʐˈˌʰʷ˞'̩'ᵻ̆'͡123456"

# new_en
# _pad        = '_'
# _punctuation = '<>[]\'* '
# _letters = 'aáàảãạăắằẳẵặâấầẩẫậbcdđeéèẻẽẹêếềểễệfghiíìỉĩịjklmnoóòỏõọôốồổỗộơớờởỡợqprstuúùủũụưứừửữựvwxyýỳỷỹỵzM'
# _letters_ipa = "θɑæɔʤəɛɪɯŋɲʂʃʈʧʊɣɤʐˈˌʰʷ˞'̩'ᵻ̆'͡123456"


# PL_BERT
_pad        = '_'
_punctuation = '<>[]\'* '
_letters = 'aáàảãạăắằẳẵặâấầẩẫậbcdđeéèẻẽẹêếềểễệfghiíìỉĩịjklmnoóòỏõọôốồổỗộơớờởỡợqprstuúùủũụưứừửữựvwxyýỳỷỹỵzM'
_letters_ipa = "ɑæɔʤəɛɪɯŋɲʂʃʈʧʊɣɤʐˈˌʰʷ˞'̩'ᵻ̆'͡123456"

#_letters = 'aáăặấbcdđefghijklmnoóôớờprstuữvwxyz'
#_letters = 'aảúáăặấbcdđefghijklmnoóôớờprstuữvwxyz'



# Export all symbols:
symbols = [_pad] + list(_punctuation) + list(_letters) + list(_letters_ipa)

# Special symbol ids
SPACE_ID = symbols.index(" ")