wx44wx/pipecat
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Adding hindi danda symbol as end of sentence marker

Browse Source
This commit is contained in:
vengadanathan srinivasan
2025-01-25 09:48:24 +05:30
parent b881dd57b3
commit 7a0cfc8d3d
2 changed files with 12 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
src/pipecat/utils/string.py
View File

@@ -14,7 +14,7 @@ ENDOFSENTENCE_PATTERN_STR = r"""
(?<!Mrs) # Negative lookbehind: not preceded by "Mrs"
(?<!Prof) # Negative lookbehind: not preceded by "Prof"
[\.\?\!:;]| # Match a period, question mark, exclamation point, colon, or semicolon
[。？！：；] # the full-width version (mainly used in East Asian languages such as Chinese)
[。？！：；।] # the full-width version (mainly used in East Asian languages such as Chinese, Hindi)
$ # End of string
"""
ENDOFSENTENCE_PATTERN = re.compile(ENDOFSENTENCE_PATTERN_STR, re.VERBOSE)