deepgeek/CosyVoice
2
0
Fork 0
mirror of https://github.com/FunAudioLLM/CosyVoice.git synced 2026-02-04 17:39:25 +08:00
Code Issues Packages Projects Releases Wiki Activity

Update frontend_utils.py

Browse Source 
"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:
zhuyunfeng
2024-09-29 14:19:31 +08:00
committed by GitHub
parent 8555ab4ded
commit 9c0aa1918b
1 changed files with 8 additions and 5 deletions
Download Patch File Download Diff File Expand all files Collapse all files

13
cosyvoice/utils/frontend_utils.py
View File

@@ -80,6 +80,13 @@ def split_paragraph(text: str, tokenize, lang="zh", token_max_n=80, token_min_n=
pounc = ['.', '?', '!', ';', ':'] pounc = ['.', '?', '!', ';', ':']
if comma_split: if comma_split:
pounc.extend(['，', ',']) pounc.extend(['，', ','])
if text[-1] not in pounc:
if lang == "zh":
text += "。"
else:
text += "."
st = 0 st = 0
utts = [] utts = []
for i, c in enumerate(text): 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 st = i + 2
else: else:
st = i + 1 st = i + 1
if len(utts) == 0:
if lang == "zh":
utts.append(text + '。')
else:
utts.append(text + '.')
final_utts = [] final_utts = []
cur_utt = "" cur_utt = ""
for utt in utts: for utt in utts: