mirror of
https://github.com/FunAudioLLM/CosyVoice.git
synced 2026-02-04 17:39:25 +08:00
Update frontend_utils.py
"Fix the bug in `split_paragraph` where the last sentence of synthesized text with multiple paragraphs loses punctuation, causing it to be lost."
This commit is contained in:
@@ -80,6 +80,13 @@ def split_paragraph(text: str, tokenize, lang="zh", token_max_n=80, token_min_n=
|
||||
pounc = ['.', '?', '!', ';', ':']
|
||||
if comma_split:
|
||||
pounc.extend([',', ','])
|
||||
|
||||
if text[-1] not in pounc:
|
||||
if lang == "zh":
|
||||
text += "。"
|
||||
else:
|
||||
text += "."
|
||||
|
||||
st = 0
|
||||
utts = []
|
||||
for i, c in enumerate(text):
|
||||
@@ -92,11 +99,7 @@ def split_paragraph(text: str, tokenize, lang="zh", token_max_n=80, token_min_n=
|
||||
st = i + 2
|
||||
else:
|
||||
st = i + 1
|
||||
if len(utts) == 0:
|
||||
if lang == "zh":
|
||||
utts.append(text + '。')
|
||||
else:
|
||||
utts.append(text + '.')
|
||||
|
||||
final_utts = []
|
||||
cur_utt = ""
|
||||
for utt in utts:
|
||||
|
||||
Reference in New Issue
Block a user