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

2
CHANGELOG.md
View File

@@ -56,6 +56,8 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
### Changed ### Changed
- We don't consider a colon `:` and end of sentence any more.
- Updated `DailyTransport` to respect the `audio_in_stream_on_start` field, - Updated `DailyTransport` to respect the `audio_in_stream_on_start` field,
ensuring it only starts receiving the audio input if it is enabled. ensuring it only starts receiving the audio input if it is enabled.

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

2
tests/test_utils_string.py
View File

@@ -14,7 +14,6 @@ class TestUtilsString(unittest.IsolatedAsyncioTestCase):
assert match_endofsentence("This is a sentence.") assert match_endofsentence("This is a sentence.")
assert match_endofsentence("This is a sentence! ") assert match_endofsentence("This is a sentence! ")
assert match_endofsentence("This is a sentence?") assert match_endofsentence("This is a sentence?")
assert match_endofsentence("This is a sentence:")
assert match_endofsentence("This is a sentence;") assert match_endofsentence("This is 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,")
@@ -33,7 +32,6 @@ class TestUtilsString(unittest.IsolatedAsyncioTestCase):
"你好！", "你好！",
"吃了吗？", "吃了吗？",
"安全第一；", "安全第一；",
"他说：",
] ]
for i in chinese_sentences: for i in chinese_sentences:
assert match_endofsentence(i) assert match_endofsentence(i)