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

add full-width punctuations as end of the sentence

Browse Source
This commit is contained in:
duyalei
2024-09-23 16:34:31 +08:00
parent 9a4e749c7c
commit 4533ed014f
2 changed files with 15 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
src/pipecat/utils/string.py
View File

@@ -14,7 +14,8 @@ ENDOFSENTENCE_PATTERN_STR = r"""
(?<!Mr|Ms|Dr) # Negative lookbehind: not preceded by Mr, Ms, Dr (combined bc. length is the same)
(?<!Mrs) # Negative lookbehind: not preceded by "Mrs"
(?<!Prof) # Negative lookbehind: not preceded by "Prof"
[\.\?\!:] # Match a period, question mark, exclamation point, or colon
[\.\?\!:;]| # Match a period, question mark, exclamation point, colon, or semicolon
[。？！：；] # the full-width version (mainly used in East Asian languages such as Chinese)
$ # End of string
"""
ENDOFSENTENCE_PATTERN = re.compile(ENDOFSENTENCE_PATTERN_STR, re.VERBOSE)