mirror of
https://github.com/storytold/storyteller-ml.git
synced 2026-10-16 00:13:07 +00:00
Brandon Thomas
23 lines
1.0 KiB
Python
23 lines
1.0 KiB
Python
""" from https://github.com/keithito/tacotron """
|
|
|
|
'''
|
|
Defines the set of symbols used in text input to the model.
|
|
|
|
The default is a set of ASCII characters that works well for English or text that has been run through Unidecode. For other data, you can modify _characters. See TRAINING_DATA.md for details. '''
|
|
from text import cmudict
|
|
|
|
_pad = '_'
|
|
bos = '^'
|
|
eos = '~'
|
|
_punctuation = ';:,.!?¡¿—…"«»“” '
|
|
_special = '-'
|
|
_letters = 'ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz'
|
|
_letters_ipa = "ɑɐɒæɓʙβɔɕçɗɖðʤəɘɚɛɜɝɞɟʄɡɠɢʛɦɧħɥʜɨɪʝɭɬɫɮʟɱɯɰŋɳɲɴøɵɸθœɶʘɹɺɾɻʀʁɽʂʃʈʧʉʊʋⱱʌɣɤʍχʎʏʑʐʒʔʡʕʢǀǁǂǃˈˌːˑʼʴʰʱʲʷˠˤ˞↓↑→↗↘'̩'ᵻ"
|
|
|
|
|
|
# Prepend "@" to ARPAbet symbols to ensure uniqueness (some are the same as uppercase letters):
|
|
_arpabet = ['@' + s for s in cmudict.valid_symbols]
|
|
|
|
# Export all symbols:
|
|
symbols = [_pad] + list(bos) + list(eos) + list(_special) + list(_punctuation) + list(_letters) + list(_letters_ipa) + _arpabet
|