utils: don't consider colon an end of sentence

CHANGELOG.md

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

src/pipecat/utils/string.py

@@ -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)

tests/test_utils_string.py

@@ -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 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！",
             "吃了吗？",
             "安全第一；",
-            "他说：",
         ]
         for i in chinese_sentences:
             assert match_endofsentence(i)