diff --git a/text/symbols.py b/text/symbols.py index 7212f92..1be47bf 100644 --- a/text/symbols.py +++ b/text/symbols.py @@ -7,11 +7,12 @@ The default is a set of ASCII characters that works well for English or text tha from text import cmudict _pad = '_' -_eos = '~' -_characters = 'ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz!\'(),-.:;? ' +_punctuation = '!\'(),.:;? ' +_special = '-' +_letters = '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 +symbols = [_pad] + list(_special) + list(_punctuation) + list(_letters) + _arpabet