blackteay/GPT-SoVITS
1
0
Fork 0
mirror of https://github.com/RVC-Boss/GPT-SoVITS.git synced 2025-10-06 22:50:00 +08:00
Code Issues Packages Projects Releases Wiki Activity

Fix bug processing duplicate punctuation in TextPreprocessor.py

Browse Source 
Strings like 'then, he' were being compressed to 'then,he' which reduced audio quality.
This commit is contained in:
Beau Horenberger 2025-01-03 13:11:38 -08:00 committed by GitHub
parent a1fe2267af
commit 86b843d259
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 7 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

12
GPT_SoVITS/TTS_infer_pack/TextPreprocessor.py
View File

@ -20,7 +20,7 @@ from tools.i18n.i18n import I18nAuto, scan_language_list
language=os.environ.get("language","Auto") language=os.environ.get("language","Auto")
language=sys.argv[-1] if sys.argv[-1] in scan_language_list() else language language=sys.argv[-1] if sys.argv[-1] in scan_language_list() else language
i18n = I18nAuto(language=language) i18n = I18nAuto(language=language)
punctuation = set(['!', '?', '…', ',', '.', '-'," "]) punctuation = set(['!', '?', '…', ',', '.', '-'])
def get_first(text:str) -> str: def get_first(text:str) -> str:
pattern = "[" + "".join(re.escape(sep) for sep in splits) + "]" pattern = "[" + "".join(re.escape(sep) for sep in splits) + "]"
@ -234,11 +234,13 @@ class TextPreprocessor:
return _text return _text
def replace_consecutive_punctuation(self,text): def replace_consecutive_punctuation(self, text):
# Collapse consecutive punctuation marks
punctuations = ''.join(re.escape(p) for p in punctuation) punctuations = ''.join(re.escape(p) for p in punctuation)
pattern = f'([{punctuations}])([{punctuations}])+' pattern = f'([{punctuations}])([{punctuations}])+'
result = re.sub(pattern, r'\1', text) text = re.sub(pattern, r'\1', text)
return result
# Collapse multiple spaces to a single space
text = re.sub(r'\s+', ' ', text)
return text