Open-source speech recognition toolkit for training, inference, streaming ASR, VAD, punctuation, speaker diarization pipelines, and OpenAI-compatible/MCP serving.
Python asraudiochineseemotion-recognitionfunasrmcp-servermultilingual-asropenai-compatible-apiparaformerpunctuationpytorchreal-time-asrspeaker-diarizationspeech-recognitionspeech-to-textstreaming-asrtranscriptionvllmvoice-activity-detectionwhisper-alternative
docs: retain MOSS deployment and identity boundaries
LauraGPT524b3e7b7a9f
diff --cc tests/test_moss_transcribe_diarize_docs.pyindex 52de59482,272b44c20..dd20782e1--- a/tests/test_moss_transcribe_diarize_docs.py+++ b/tests/test_moss_transcribe_diarize_docs.py@@@ -163,23 -178,18 +181,40 @@@ def test_openai_consumer_docs_expose_moassert "moss-transcribe-diarize" in model["enum"]+def test_use_case_showcases_surface_offline_moss_diarization() -> None:+ showcases = {+ "docs/use_case_showcase.md": (+ "Offline long-form diarized transcripts",+ "offline long audio",+ "anonymous speaker labels",+ ),+ "docs/use_case_showcase_zh.md": (+ "离线长音频一体化转写与说话人标签",+ "离线长音频",+ "匿名说话人标签",+ ),+ }++ for name, markers in showcases.items():+ text = (ROOT / name).read_text()+ assert "MOSS-Transcribe-Diarize" in text, name+ assert "moss_transcribe_diarize" in text, name+ for marker in markers:+ assert marker in text, name+++++ def test_moss_docs_describe_anonymous_labels_not_known_person_identity() -> None:+ combined = "\n".join(path.read_text(encoding="utf-8") for path in BOUNDARY_DOCS)++ for misleading_claim in (+ "speaker identity",+ "speaker identities",+ "说话人身份",+ "身份识别",+ ):+ assert misleading_claim not in combined++ assert "anonymous speaker labels" in combined+ assert "匿名说话人标签" in combined+ assert "does not identify a known person" in combined+ assert "不能识别已知人物" in combined