2021-08-07 11:56:00 +08:00
|
|
|
"""
|
|
|
|
|
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 . import cmudict
|
|
|
|
|
|
|
|
|
|
_pad = "_"
|
|
|
|
|
_eos = "~"
|
2021-08-22 23:44:25 +08:00
|
|
|
_characters = 'ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz1234567890!\'(),-.:;? '
|
2021-08-29 00:45:49 +08:00
|
|
|
|
|
|
|
|
#_characters = 'ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz12340!\'(),-.:;? ' # use this old one if you want to train old model
|
2021-08-07 11:56:00 +08:00
|
|
|
# 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
|
