fix(postprocess): keep a space between Latin VAD segments in rich transcription

funasr/utils/postprocess_utils.py

@@ -442,6 +442,11 @@ def format_str_v2(s):
     return s.strip()
 
 
+def _is_spaced_char(ch):
+    """Latin and Hangul text separates words with spaces; CJK text does not."""
+    return (ch.isascii() and not ch.isspace()) or "\uac00" <= ch <= "\ud7a3"
+
+
 def rich_transcription_postprocess(s):
     """Rich transcription postprocess.
 
@@ -481,6 +486,10 @@ def get_event(s):
         cur_ent_event = get_event(s_list[i])
         if get_emo(s_list[i]) != None and get_emo(s_list[i]) == get_emo(new_s):
             new_s = new_s[:-1]
-        new_s += s_list[i].strip().lstrip()
+        segment = s_list[i].strip()
+        # Each VAD segment is its own <|lang|> block; keep the word boundary between them.
+        if segment and _is_spaced_char(new_s[-1]) and _is_spaced_char(segment[0]):
+            new_s += " "
+        new_s += segment
     new_s = new_s.replace("The.", " ")
     return new_s.strip()

runtime/python/libtorch/funasr_torch/utils/postprocess_utils.py

@@ -346,6 +346,11 @@ def format_str_v2(s):
     return s.strip()
 
 
+def _is_spaced_char(ch):
+    """Latin and Hangul text separates words with spaces; CJK text does not."""
+    return (ch.isascii() and not ch.isspace()) or "\uac00" <= ch <= "\ud7a3"
+
+
 def rich_transcription_postprocess(s):
     def get_emo(s):
         return s[-1] if s[-1] in emo_set else None
@@ -370,6 +375,10 @@ def get_event(s):
         cur_ent_event = get_event(s_list[i])
         if get_emo(s_list[i]) != None and get_emo(s_list[i]) == get_emo(new_s):
             new_s = new_s[:-1]
-        new_s += s_list[i].strip().lstrip()
+        segment = s_list[i].strip()
+        # Each VAD segment is its own <|lang|> block; keep the word boundary between them.
+        if segment and _is_spaced_char(new_s[-1]) and _is_spaced_char(segment[0]):
+            new_s += " "
+        new_s += segment
     new_s = new_s.replace("The.", " ")
     return new_s.strip()

runtime/python/onnxruntime/funasr_onnx/utils/postprocess_utils.py

@@ -400,6 +400,11 @@ def format_str_v2(s):
     return s.strip()
 
 
+def _is_spaced_char(ch):
+    """Latin and Hangul text separates words with spaces; CJK text does not."""
+    return (ch.isascii() and not ch.isspace()) or "\uac00" <= ch <= "\ud7a3"
+
+
 def rich_transcription_postprocess(s):
     def get_emo(s):
         return s[-1] if s[-1] in emo_set else None
@@ -424,6 +429,10 @@ def get_event(s):
         cur_ent_event = get_event(s_list[i])
         if get_emo(s_list[i]) != None and get_emo(s_list[i]) == get_emo(new_s):
             new_s = new_s[:-1]
-        new_s += s_list[i].strip().lstrip()
+        segment = s_list[i].strip()
+        # Each VAD segment is its own <|lang|> block; keep the word boundary between them.
+        if segment and _is_spaced_char(new_s[-1]) and _is_spaced_char(segment[0]):
+            new_s += " "
+        new_s += segment
     new_s = new_s.replace("The.", " ")
     return new_s.strip()

tests/test_rich_transcription_event_segments.py

@@ -34,7 +34,9 @@ def test_repeated_event_only_segments_keep_following_text(postprocess, event, fo
 
     result = postprocess.rich_transcription_postprocess(text)
 
-    assert result == postprocess.event_dict[event] + "hello" + following_text
+    assert result == postprocess.event_dict[event] + " ".join(
+        filter(None, ["hello", following_text])
+    )
 
 
 @pytest.mark.parametrize("event", ["<|Cough|>", "<|Sneeze|>", "<|Applause|>"])

tests/test_rich_transcription_postprocess.py

@@ -32,3 +32,24 @@ def test_cough_and_sneeze_events_render_distinct_emojis(path, event, emoji):
     text = module.rich_transcription_postprocess(f"<|en|><|NEUTRAL|>{event}<|woitn|>hello")
 
     assert text == f"{emoji}hello"
+
+
+@pytest.mark.parametrize("path", POSTPROCESS_UTILS, ids=lambda path: path.parts[-3])
+@pytest.mark.parametrize(
+    "first, second, expected",
+    [
+        ("Hello world.", "How are you?", "Hello world. How are you?"),
+        ("so I went to the", "store", "so I went to the store"),
+        ("안녕하세요.", "감사합니다.", "안녕하세요. 감사합니다."),
+        ("你好。", "再见。", "你好。再见。"),
+        ("你好。", "Hello.", "你好。Hello."),
+    ],
+)
+def test_vad_segments_keep_a_space_between_spaced_scripts(path, first, second, expected):
+    module = _load(path)
+    tags = "<|NEUTRAL|><|Speech|><|withitn|>"
+
+    # AutoModel joins the tagged text of each VAD segment with a single space.
+    text = module.rich_transcription_postprocess(f"<|en|>{tags}{first} <|en|>{tags}{second}")
+
+    assert text == expected