You can not select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
17 lines
681 B
17 lines
681 B
""" 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 = '_'
|
|
_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
|