Simonlob's picture
Second
cf1295a
raw
history blame
630 Bytes
""" from https://github.com/keithito/tacotron
Defines the set of symbols used in text input to the model.
"""
_pad = "_"
_punctuation = ';:,.!?¡¿—…"«»“” '
_letters = "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz"
_letters_ipa = (
"ɑɐɒæɓʙβɔɕçɗɖðʤəɘɚɛɜɝɞɟʄɡɠɢʛɦɧħɥʜɨɪʝɭɬɫɮʟɱɯɰŋɳɲɴøɵɸθœɶʘɹɺɾɻʀʁɽʂʃʈʧʉʊʋⱱʌɣɤʍχʎʏʑʐʒʔʡʕʢǀǁǂǃˈˌːˑʼʴʰʱʲʷˠˤ˞↓↑-1['̩'ᵻ"
)
# Export all symbols:
symbols = [_pad] + list(_punctuation) + list(_letters) + list(_letters_ipa)
# Special symbol ids
SPACE_ID = symbols.index(" ")