ulysses115's picture
First model version
71b467a
raw
history blame
851 Bytes
""" from https://github.com/keithito/tacotron """
'''
Defines the set of symbols used in text input to the model.
'''
_pad = '_'
_punctuation = ';:,.!?¡¿—…"«»“” '
_punctuation_zh = ';:,。!?-“”《》、()BP…—~.\·『』・ '
_letters = 'ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz'
_numbers = '1234567890'
_others = ''
_letters_ipa = "ɑɐɒæɓʙβɔɕçɗɖðʤəɘɚɛɜɝɞɟʄɡɠɢʛɦɧħɥʜɨɪʝɭɬɫɮʟɱɯɰŋɳɲɴøɵɸθœɶʘɹɺɾɻʀʁɽʂʃʈʧʉʊʋⱱʌɣɤʍχʎʏʑʐʒʔʡʕʢǀǁǂǃˈˌːˑʼʴʰʱʲʷˠˤ˞↓↑→↗↘'̩'ᵻ"
# Export all symbols:
symbols = [_pad] + list(_punctuation) + list(_letters) + list(_letters_ipa)
symbols_zh = [_pad] + list(_punctuation_zh) + list(_letters) + list(_numbers)
# Special symbol ids
SPACE_ID = symbols.index(" ")