MockingBird/synthesizer/utils/symbols.py

17 lines
635 B
Python
Raw Normal View History

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 = "~"
_characters = 'ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz12340!\'(),-.:;? '
# 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