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

Merge pull request #1269 from pipecat-ai/aleix/endofsentence-support-ellipses

Browse Source 
utils: add support for ellipses in match_endofsentence()
This commit is contained in:
Aleix Conchillo Flaqué
2025-02-21 15:08:22 -08:00
committed by GitHub
parent 4acf7296e0 12bce2e8c0
commit d6dc37f0b6
3 changed files with 10 additions and 6 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
CHANGELOG.md
View File

@@ -36,6 +36,8 @@ stt = DeepgramSTTService(..., live_options=LiveOptions(model="nova-2-general"))
### Fixed ### Fixed
- Fixed `match_endofsentence` support for ellipses.
- Fixed an issue that would cause undesired interruptions via - Fixed an issue that would cause undesired interruptions via
`EmulateUserStartedSpeakingFrame` when only interim transcriptions (i.e. no `EmulateUserStartedSpeakingFrame` when only interim transcriptions (i.e. no
final transcriptions) where received. final transcriptions) where received.

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

10
tests/test_utils_string.py
View File

@@ -11,10 +11,12 @@ from pipecat.utils.string import match_endofsentence
class TestUtilsString(unittest.IsolatedAsyncioTestCase): class TestUtilsString(unittest.IsolatedAsyncioTestCase):
async def test_endofsentence(self): async def test_endofsentence(self):
assert match_endofsentence("This is a sentence.") assert match_endofsentence("This is a sentence.") == 19
assert match_endofsentence("This is a sentence! ") assert match_endofsentence("This is a sentence!") == 19
assert match_endofsentence("This is a sentence?") assert match_endofsentence("This is a sentence?") == 19
assert match_endofsentence("This is a sentence;") assert match_endofsentence("This is a sentence;") == 19
assert match_endofsentence("This is a sentence...") == 21
assert match_endofsentence("This is a sentence . . .") == 24
assert not match_endofsentence("This is not a sentence") assert not match_endofsentence("This is not a sentence")
assert not match_endofsentence("This is not a sentence,") assert not match_endofsentence("This is not a sentence,")
assert not match_endofsentence("This is not a sentence, ") assert not match_endofsentence("This is not a sentence, ")