mirror of https://github.com/coqui-ai/TTS.git
22 lines
693 B
Python
22 lines
693 B
Python
# -*- coding: utf-8 -*-
|
|
'''
|
|
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 utils.text import cmudict
|
|
|
|
_pad = '_'
|
|
_eos = '~'
|
|
_characters = 'ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz!\'(),-.:;? '
|
|
|
|
# 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, _eos] + list(_characters) + _arpabet
|
|
|
|
if __name__ == '__main__':
|
|
print(symbols)
|