Spaces:
Running
Running
| # Copyright (c) 2023 Amphion. | |
| # | |
| # This source code is licensed under the MIT license found in the | |
| # LICENSE file in the root directory of this source tree. | |
| """ This code is modified 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, pinyin | |
| _pad = "_" | |
| _punctuation = "!'(),.:;? " | |
| _special = "-" | |
| _letters = "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz" | |
| _silences = ["@sp", "@spn", "@sil"] | |
| # Prepend "@" to ARPAbet symbols to ensure uniqueness (some are the same as uppercase letters): | |
| _arpabet = ["@" + s for s in cmudict.valid_symbols] | |
| _pinyin = ["@" + s for s in pinyin.valid_symbols] | |
| # Export all symbols: | |
| symbols = ( | |
| [_pad] | |
| + list(_special) | |
| + list(_punctuation) | |
| + list(_letters) | |
| + _arpabet | |
| + _silences | |
| # + _pinyin # for chinese | |
| ) | |