mirror of
https://github.com/malarinv/tacotron2
synced 2026-03-08 09:42:34 +00:00
adding changes to text
This commit is contained in:
@@ -37,8 +37,6 @@ def text_to_sequence(text, cleaner_names):
|
||||
sequence += _arpabet_to_sequence(m.group(2))
|
||||
text = m.group(3)
|
||||
|
||||
# Append EOS token
|
||||
sequence.append(_symbol_to_id['~'])
|
||||
return sequence
|
||||
|
||||
|
||||
|
||||
@@ -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
|
||||
|
||||
Reference in New Issue
Block a user