Merge pull request #1090 from vengad-arrowhead/main

Adding hindi danda symbol as end of sentence marker

src/pipecat/utils/string.py

@@ -14,7 +14,7 @@ ENDOFSENTENCE_PATTERN_STR = r"""
     (?<!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)
+    [。？！：；।]       # 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

@@ -38,3 +38,14 @@ class TestUtilsString(unittest.IsolatedAsyncioTestCase):
         for i in chinese_sentences:
             assert match_endofsentence(i)
         assert not match_endofsentence("你好，")
+
+    async def test_endofsentence_hi(self):
+        hindi_sentences = [
+            "हैलो।",
+            "हैलो！",
+            "आप खाये हैं？",
+            "सुरक्षा पहले।",
+        ]
+        for i in hindi_sentences:
+            assert match_endofsentence(i)
+        assert not match_endofsentence("हैलो，")