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

utils: don't consider colon an end of sentence

Browse Source
This commit is contained in:
Aleix Conchillo Flaqué
2025-02-14 15:44:13 -08:00
parent 633a4d4c58
commit f6912c0f9a
3 changed files with 4 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
src/pipecat/utils/string.py
View File

@@ -13,8 +13,8 @@ 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, colon, or semicolon
[。？！：；।] # the full-width version (mainly used in East Asian languages such as Chinese, Hindi)
[\.\?\!;]| # Match a period, question mark, exclamation point, or semicolon
[。？！；।] # 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)