mirror of https://github.com/malarinv/tacotron2
adding changes to text
parent
f03692c73d
commit
e0c7e0e928
|
|
@ -37,8 +37,6 @@ def text_to_sequence(text, cleaner_names):
|
||||||
sequence += _arpabet_to_sequence(m.group(2))
|
sequence += _arpabet_to_sequence(m.group(2))
|
||||||
text = m.group(3)
|
text = m.group(3)
|
||||||
|
|
||||||
# Append EOS token
|
|
||||||
sequence.append(_symbol_to_id['~'])
|
|
||||||
return sequence
|
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
|
from text import cmudict
|
||||||
|
|
||||||
_pad = '_'
|
_pad = '_'
|
||||||
_eos = '~'
|
_punctuation = '!\'(),.:;? '
|
||||||
_characters = 'ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz!\'(),-.:;? '
|
_special = '-'
|
||||||
|
_letters = 'ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz'
|
||||||
|
|
||||||
# Prepend "@" to ARPAbet symbols to ensure uniqueness (some are the same as uppercase letters):
|
# Prepend "@" to ARPAbet symbols to ensure uniqueness (some are the same as uppercase letters):
|
||||||
_arpabet = ['@' + s for s in cmudict.valid_symbols]
|
_arpabet = ['@' + s for s in cmudict.valid_symbols]
|
||||||
|
|
||||||
# Export all symbols:
|
# Export all symbols:
|
||||||
symbols = [_pad, _eos] + list(_characters) + _arpabet
|
symbols = [_pad] + list(_special) + list(_punctuation) + list(_letters) + _arpabet
|
||||||
|
|
|
||||||
Loading…
Reference in New Issue