Merge pull request #286 from TomTom101/feat/regex_endofsentence

fix: No more falsely detect a sentence end on "U.S.A", "3:00 a.m."

src/pipecat/services/ai_services.py

@@ -28,6 +28,24 @@
 from pipecat.processors.frame_processor import FrameDirection, FrameProcessor
 from pipecat.utils.audio import calculate_audio_volume
 from pipecat.utils.utils import exp_smoothing
+import re
+
+
+ENDOFSENTENCE_PATTERN_STR = r"""
+    (?<![A-Z])       # Negative lookbehind: not preceded by an uppercase letter (e.g., "U.S.A.")
+    (?<!\d)          # Negative lookbehind: not preceded by a digit (e.g., "1. Let's start")
+    (?<!\d\s[ap])    # Negative lookbehind: not preceded by time (e.g., "3:00 a.m.")
+    (?<!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
+    $                # End of string
+"""
+ENDOFSENTENCE_PATTERN = re.compile(ENDOFSENTENCE_PATTERN_STR, re.VERBOSE)
+
+
+def match_endofsentence(text: str) -> bool:
+    return ENDOFSENTENCE_PATTERN.search(text.rstrip()) is not None
 
 
 class AIService(FrameProcessor):
@@ -137,9 +155,7 @@ async def _process_text_frame(self, frame: TextFrame):
             text = frame.text
         else:
             self._current_sentence += frame.text
-            if self._current_sentence.strip().endswith(
-                    (".", "?", "!")) and not self._current_sentence.strip().endswith(
-                    ("Mr,", "Mrs.", "Ms.", "Dr.")):
+            if match_endofsentence(self._current_sentence):
                 text = self._current_sentence
                 self._current_sentence = ""
 

tests/test_ai_services.py

@@ -2,8 +2,8 @@
 
 from typing import AsyncGenerator
 
-from pipecat.services.ai_services import AIService
-from pipecat.pipeline.frames import EndFrame, Frame, TextFrame
+from pipecat.services.ai_services import AIService, match_endofsentence
+from pipecat.frames.frames import EndFrame, Frame, TextFrame
 
 
 class SimpleAIService(AIService):
@@ -27,6 +27,22 @@ async def test_simple_processing(self):
 
         self.assertEqual(input_frames, output_frames)
 
+    async def test_endofsentence(self):
+        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("Ok, Mr. Smith let's ")
+        assert not match_endofsentence("Dr. Walker, I presume ")
+        assert not match_endofsentence("Prof. Walker, I presume ")
+        assert not match_endofsentence("zweitens, und 3.")
+        assert not match_endofsentence("Heute ist Dienstag, der 3.")  # 3. Juli 2024
+        assert not match_endofsentence("America, or the U.")  # U.S.A.
+        assert not match_endofsentence("It still early, it's 3:00 a.")  # 3:00 a.m.
+
 
 if __name__ == "__main__":
     unittest.main()