Skip to content

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

fix: drop the leading space on Latin sentence timestamps

Ting Zhang245ee66ac8fa
diff --git a/funasr/utils/timestamp_tools.py b/funasr/utils/timestamp_tools.py
index b97e405f3..8009ec757 100644
--- a/funasr/utils/timestamp_tools.py
+++ b/funasr/utils/timestamp_tools.py
@@ -189,6 +189,11 @@ def timestamp_sentence(
punc_id = int(punc_id) if punc_id is not None else 1
sentence_end = timestamp[1] if timestamp is not None else sentence_end
+ # Latin tokens are inserted with a leading space. Drop one leading
+ # space, as timestamp_sentence_en does, so a sentence that starts
+ # with an English word is not stored as " iphone...".
+ if sentence_text.startswith(" "):
+ sentence_text = sentence_text[1:]
if punc_id > 1:
sentence_text += punc_list[punc_id - 2]
if sentence_text_seg.endswith(" "):
diff --git a/tests/test_timestamp_tools.py b/tests/test_timestamp_tools.py
index a9dd41d18..763c14e19 100644
--- a/tests/test_timestamp_tools.py
+++ b/tests/test_timestamp_tools.py
@@ -57,6 +57,31 @@ def test_timestamp_sentence_en_missing_trailing_timestamp_matches_zh_fallback():
assert en_result[1]["start"] == zh_result[1]["start"]
+def test_timestamp_sentence_does_not_prefix_latin_text_with_a_space():
+ mixed = timestamp_sentence(
+ punc_id_list=[1, 2, 1, 1, 3],
+ timestamp_postprocessed=[[0, 100], [100, 200], [200, 300], [300, 400], [400, 500]],
+ text_postprocessed="我 用 iphone pro max",
+ return_raw_text=True,
+ )
+ assert [sentence["text"] for sentence in mixed] == ["我用,", "iphone pro max。"]
+ assert [sentence["raw_text"] for sentence in mixed] == ["我 用", "iphone pro max"]
+
+ english = timestamp_sentence(
+ [1, 3, 1],
+ [[0, 100], [100, 200], [200, 300]],
+ "hello world again",
+ )
+ assert [sentence["text"] for sentence in english] == ["hello world。", "again"]
+
+ chinese = timestamp_sentence(
+ [1, 3],
+ [[0, 100], [100, 200]],
+ "你好 世界",
+ )
+ assert chinese[0]["text"] == "你好世界。"
+
+
def test_timestamp_sentence_raw_text_keeps_token_separators():
result = timestamp_sentence(
punc_id_list=[1, 2, 1, 1, 3],