From 7a0cfc8d3dd11375e84f578181c2dcbc01a4fe45 Mon Sep 17 00:00:00 2001
From: vengadanathan srinivasan
 <vengadanathansrinivasan@vengadanathans-MacBook-Pro-2.local>
Date: Sat, 25 Jan 2025 09:48:24 +0530
Subject: [PATCH] Adding hindi danda symbol as end of sentence marker

---
 src/pipecat/utils/string.py |  2 +-
 tests/test_utils_string.py  | 11 +++++++++++
 2 files changed, 12 insertions(+), 1 deletion(-)

diff --git a/src/pipecat/utils/string.py b/src/pipecat/utils/string.py
index c901586f7..c269c5e57 100644
--- a/src/pipecat/utils/string.py
+++ b/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)
diff --git a/tests/test_utils_string.py b/tests/test_utils_string.py
index 9587544a1..aa135a639 100644
--- a/tests/test_utils_string.py
+++ b/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，")