Skip to content

Open-source speech recognition toolkit for training, inference, streaming ASR, VAD, punctuation, speaker diarization pipelines, and OpenAI-compatible/MCP serving.

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

David-Wu1119c660e192719b
diff --git a/funasr/utils/postprocess_utils.py b/funasr/utils/postprocess_utils.py
index 6a3cd2336..cd99e1fbb 100644
--- a/funasr/utils/postprocess_utils.py
+++ b/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 rich_transcription_postprocess(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()
diff --git a/runtime/python/libtorch/funasr_torch/utils/postprocess_utils.py b/runtime/python/libtorch/funasr_torch/utils/postprocess_utils.py
index 3f8d9999e..d9e1b0643 100644
--- a/runtime/python/libtorch/funasr_torch/utils/postprocess_utils.py
+++ b/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 rich_transcription_postprocess(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()
diff --git a/runtime/python/onnxruntime/funasr_onnx/utils/postprocess_utils.py b/runtime/python/onnxruntime/funasr_onnx/utils/postprocess_utils.py
index 343ed383a..84e220166 100644
--- a/runtime/python/onnxruntime/funasr_onnx/utils/postprocess_utils.py
+++ b/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 rich_transcription_postprocess(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()
diff --git a/tests/test_rich_transcription_event_segments.py b/tests/test_rich_transcription_event_segments.py
index ed756abfd..a565b5c3c 100644
--- a/tests/test_rich_transcription_event_segments.py
+++ b/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|>"])
diff --git a/tests/test_rich_transcription_postprocess.py b/tests/test_rich_transcription_postprocess.py
index 8e07de09e..2cfc708ad 100644
--- a/tests/test_rich_transcription_postprocess.py
+++ b/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"
+
+
[email protected]("path", POSTPROCESS_UTILS, ids=lambda path: path.parts[-3])
+ "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