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(moss): expose AutoModel deployment contract
LauraGPTdb2639d47cec
diff --git a/web-pages/product-site/data/deployments.json b/web-pages/product-site/data/deployments.jsonindex a9ffbde15..80bdd6afc 100644--- a/web-pages/product-site/data/deployments.json+++ b/web-pages/product-site/data/deployments.json@@ -13,7 +13,7 @@"models": ["OpenMOSS-Team/MOSS-Transcribe-Diarize (third-party Apache-2.0 model)"],"operating_systems": ["Linux"],"interfaces": ["OpenAI-compatible HTTP", "vLLM", "SGLang Omni", "Transformers"],- "tested": {"funasr": "ecosystem contract; third-party model@e8681d68", "runtime": "vLLM 0.23.1rc1.dev949+g68b4a1d58 / Torch 2.11.0+cu129 / H100 80GB", "verified": "2026-08-29"},+ "tested": {"funasr": "AutoModel adapter@a3a2de0a; third-party model@e8681d68", "runtime": "Transformers 5.16.1 + vLLM 0.23.1rc1.dev949+g68b4a1d58 / Torch 2.11.0+cu129 / H100 80GB", "verified": "2026-08-29"},"commands": {"install": ["uv venv --python 3.12 .venv-moss && uv pip install --python .venv-moss/bin/python -U 'vllm[audio]' --torch-backend=auto --extra-index-url https://wheels.vllm.ai/68b4a1d582818e67adc903bf1b8fc5a5447da2fa/cu129",@@ -28,7 +28,8 @@],"smoke": ["curl -fsS http://127.0.0.1:8898/v1/audio/transcriptions -F file=@runtime/llama.cpp/tests/sample.wav -F model=moss-transcribe-diarize -F response_format=json -F temperature=0 | tee /tmp/moss-transcription.json",- "python - <<'PY'\nimport json\n\nwith open('/tmp/moss-transcription.json', encoding='utf-8') as stream:\n payload = json.load(stream)\ntext = payload.get('text', '')\nassert text.strip(), payload\nassert '[S01]' in text, text\nprint(text)\nPY"+ "python - <<'PY'\nimport json\n\nwith open('/tmp/moss-transcription.json', encoding='utf-8') as stream:\n payload = json.load(stream)\ntext = payload.get('text', '')\nassert text.strip(), payload\nassert '[S01]' in text, text\nprint(text)\nPY",+ "python - <<'PY'\nfrom funasr import AutoModel\n\nmodel = AutoModel(model='OpenMOSS-Team/MOSS-Transcribe-Diarize', backend='vllm', vllm_base_url='http://127.0.0.1:8898/v1', vllm_model='moss-transcribe-diarize', disable_update=True)\nresult = model.generate('runtime/llama.cpp/tests/sample.wav')[0]\nassert result['raw_text'] and result['sentence_info'], result\nprint(result['text'])\nprint(result['sentence_info'])\nPY"]},"evidence": [@@ -36,7 +37,8 @@{"label": "upstream source pinned at cb765f2", "url": "https://github.com/OpenMOSS/MOSS-Transcribe-Diarize/commit/cb765f2b0fe6f7a298aa2002e2281ae693d1f3c3"},{"label": "official model snapshot pinned at e8681d68", "url": "https://huggingface.co/OpenMOSS-Team/MOSS-Transcribe-Diarize/tree/e8681d68e7042738ffca8ac8212bc8fcb1131ab8"},{"label": "official vLLM and SGLang Omni serving guide", "url": "https://github.com/OpenMOSS/MOSS-Transcribe-Diarize/blob/cb765f2b0fe6f7a298aa2002e2281ae693d1f3c3/README.md"},- {"label": "FunASR ecosystem integration guide", "url": "https://github.com/modelscope/FunASR/blob/main/docs/moss_transcribe_diarize.md"}+ {"label": "FunASR ecosystem integration guide", "url": "https://github.com/modelscope/FunASR/blob/main/docs/moss_transcribe_diarize.md"},+ {"label": "FunASR AutoModel adapter merge and exact-head CI", "url": "https://github.com/modelscope/FunASR/pull/3558"}],"benchmarks": [{@@ -56,27 +58,27 @@"translations": {"zh": {"name": "MOSS 统一转写与说话人分离",- "summary": "在 FunASR 部署中心接入 OpenMOSS 发布的第三方 Apache-2.0 模型,一次生成长音频转写、时间戳和说话人标签。",+ "summary": "通过 FunASR AutoModel 或 OpenAI 兼容服务接入 OpenMOSS 发布的第三方 Apache-2.0 模型,一次生成长音频转写、时间戳和说话人标签。","fit": ["会议、访谈、播客和通话的多人长音频", "希望通过同一个模型输出文本、时间戳与说话人编号", "已有 NVIDIA GPU,并需要 OpenAI 兼容的音频转写接口"],- "not_fit": ["实时流式字幕或低延迟端点检测", "CPU、桌面边缘设备或 Windows 原生部署", "要求 FunASR 自有模型权重或 FunASR AutoModel API 的项目"],- "selection_reason": "模型端到端联合生成转写与说话人标签,用户不必再拼接外部 VAD、ASR 和 diarization 管线;vLLM 与 SGLang Omni 都提供 /v1/audio/transcriptions。",+ "not_fit": ["实时流式字幕或低延迟端点检测", "CPU、桌面边缘设备或 Windows 原生部署", "要求 FunASR 自有模型权重的项目"],+ "selection_reason": "模型端到端联合生成转写与说话人标签,用户不必再拼接外部 VAD、ASR 和 diarization 管线;FunASR AutoModel 为 Transformers 与 vLLM 提供统一的结构化结果。","primary_limitation": "这是 OpenMOSS 的第三方模型,不是 FunASR 模型;“无需外部 VAD”不表示模型内部没有分块或分段。当前 vLLM 路径固定 nightly commit,升级前必须重跑真实多人长音频。","status_label": "社区验证",- "operations": ["固定模型 revision、vLLM nightly commit、CUDA/Torch 与 trust_remote_code 审计结果", "用真实会议验证说话人一致性、重叠语音、长静音、时间戳和最大生成长度", "vLLM 的 json 返回原始 [Sxx] 标记文本;需要 verbose_json 结构化 speaker segments 时使用 SGLang Omni 并单独验证"],+ "operations": ["固定模型 revision、FunASR adapter merge、vLLM nightly commit、CUDA/Torch 与 trust_remote_code 审计结果", "用真实会议验证说话人一致性、重叠语音、长静音、时间戳和最大生成长度", "FunASR AutoModel 保留 raw_text,并统一返回 text、timestamp 和带 spk 的 sentence_info;直接调用 vLLM 时 json 仍是原始 [Sxx] 标记文本"],"security": ["把服务绑定内网,由网关完成认证、TLS、限流及音频大小/时长限制", "固定并审计 trust_remote_code 对应的模型 revision,不执行浮动 main 代码", "隔离模型缓存、上传临时目录和生成日志,按数据保留策略清理原始音频"],- "troubleshooting": ["启动前确认 CUDA 12 使用 cu129 nightly 源,CUDA 13 使用上游文档列出的 cu130 源", "长音频被截断时提高 max_completion_tokens,并同时监控显存、延迟和输出完整性", "vLLM json 响应没有 segments 字段是当前接口边界;从 text 解析 [start][Sxx]text[end],或改用 SGLang Omni verbose_json"]+ "troubleshooting": ["启动前确认 CUDA 12 使用 cu129 nightly 源,CUDA 13 使用上游文档列出的 cu130 源", "长音频被截断时提高 max_completion_tokens,并同时监控显存、延迟和输出完整性", "直接调用 vLLM 时 json 没有 segments 字段是当前接口边界;使用 FunASR AutoModel 归一化结果,或改用并单独验证 SGLang Omni verbose_json"]},"en": {"name": "MOSS unified transcription and diarization",- "summary": "Use the third-party Apache-2.0 model published by OpenMOSS to produce long-form transcripts, timestamps, and speaker labels in one pass from the FunASR deployment center.",+ "summary": "Use FunASR AutoModel or an OpenAI-compatible service with the third-party Apache-2.0 model published by OpenMOSS to produce long-form transcripts, timestamps, and speaker labels in one pass.","fit": ["Multi-speaker meetings, interviews, podcasts, and calls", "One model output for text, timestamps, and speaker identifiers", "NVIDIA GPU deployments that need an OpenAI-compatible audio transcription endpoint"],- "not_fit": ["Realtime streaming captions or low-latency endpoint detection", "CPU, desktop-edge, or native Windows deployments", "Projects that require FunASR-owned model weights or the FunASR AutoModel API"],- "selection_reason": "The model jointly emits transcription and speaker labels so users do not need to assemble an external VAD, ASR, and diarization pipeline; both vLLM and SGLang Omni expose /v1/audio/transcriptions.",+ "not_fit": ["Realtime streaming captions or low-latency endpoint detection", "CPU, desktop-edge, or native Windows deployments", "Projects that require FunASR-owned model weights"],+ "selection_reason": "The model jointly emits transcription and speaker labels so users do not need to assemble an external VAD, ASR, and diarization pipeline; FunASR AutoModel provides one structured result across Transformers and vLLM.","primary_limitation": "This is an OpenMOSS third-party model, not a FunASR model; no external VAD requirement does not imply an absence of internal segmentation. The vLLM path pins a nightly commit and must be revalidated on real long multi-speaker audio before upgrades.","status_label": "Community verified",- "operations": ["Pin the model revision, vLLM nightly commit, CUDA/Torch stack, and trust_remote_code audit", "Validate speaker consistency, overlap, long silence, timestamps, and generation limits on real meetings", "vLLM json returns raw [Sxx]-tagged text; use and separately validate SGLang Omni verbose_json when structured speaker segments are required"],+ "operations": ["Pin the model revision, FunASR adapter merge, vLLM nightly commit, CUDA/Torch stack, and trust_remote_code audit", "Validate speaker consistency, overlap, long silence, timestamps, and generation limits on real meetings", "FunASR AutoModel preserves raw_text and normalizes text, timestamp, and sentence_info with spk; direct vLLM json still returns raw [Sxx]-tagged text"],"security": ["Bind workers to a private network and put authentication, TLS, rate limits, and audio size/duration limits at the gateway", "Pin and audit the trust_remote_code model revision instead of executing a floating main revision", "Isolate model caches, upload directories, and generation logs; remove source audio according to retention policy"],- "troubleshooting": ["Use the cu129 nightly source for CUDA 12 and the upstream cu130 source for CUDA 13", "If long audio is truncated, raise max_completion_tokens while monitoring memory, latency, and output completeness", "A vLLM json response without segments is the current API boundary; parse [start][Sxx]text[end] from text or use SGLang Omni verbose_json"]+ "troubleshooting": ["Use the cu129 nightly source for CUDA 12 and the upstream cu130 source for CUDA 13", "If long audio is truncated, raise max_completion_tokens while monitoring memory, latency, and output completeness", "A direct vLLM json response without segments is the current API boundary; normalize it with FunASR AutoModel or use and separately validate SGLang Omni verbose_json"]}}},diff --git a/web-pages/product-site/tests/browser/product-site.spec.ts b/web-pages/product-site/tests/browser/product-site.spec.tsindex 7dc6de5b7..ce9b933c3 100644--- a/web-pages/product-site/tests/browser/product-site.spec.ts+++ b/web-pages/product-site/tests/browser/product-site.spec.ts@@ -174,6 +174,38 @@ for (const viewport of [});}+for (const viewport of [+ { name: 'mobile', width: 390, height: 844 },+ { name: 'desktop', width: 1440, height: 900 },+]) {+ test(`MOSS AutoModel deployment is stable at ${viewport.name}`, async ({ page }, testInfo) => {+ await page.setViewportSize(viewport);+ await page.goto('/deploy/moss-transcribe-diarize.html');++ await expect(page.locator('h1')).toHaveText('MOSS 统一转写与说话人分离');+ await expect(page.getByText('FunASR AutoModel', { exact: false }).first()).toBeVisible();+ await expect(page.getByText('OpenMOSS', { exact: false }).first()).toBeVisible();+ await expect(page.getByText('sentence_info', { exact: false }).first()).toBeVisible();+ await expect(page.locator('a[href="https://github.com/modelscope/FunASR/pull/3558"]')).toBeVisible();+ await expect(page.locator('a[href="/en/deploy/moss-transcribe-diarize.html"]')).toBeVisible();++ const layout = await page.evaluate(() => ({+ overflow: document.documentElement.scrollWidth - document.documentElement.clientWidth,+ commandWidths: [...document.querySelectorAll<HTMLElement>('.command-block')].map((node) => ({+ parent: node.parentElement?.getBoundingClientRect().width ?? 0,+ width: node.getBoundingClientRect().width,+ })),+ }));+ expect(layout.overflow).toBeLessThanOrEqual(1);+ expect(layout.commandWidths.every(({ parent, width }) => width <= parent + 1)).toBe(true);++ await page.screenshot({+ path: testInfo.outputPath(`moss-automodel-${viewport.name}.png`),+ fullPage: true,+ });+ });+}+for (const viewport of [{ name: 'mobile', width: 390, height: 844 },{ name: 'desktop', width: 1440, height: 900 },diff --git a/web-pages/product-site/tests/test_registry.py b/web-pages/product-site/tests/test_registry.pyindex d9509ccf4..b5a2297ea 100644--- a/web-pages/product-site/tests/test_registry.py+++ b/web-pages/product-site/tests/test_registry.py@@ -107,8 +107,8 @@ def test_moss_transcribe_diarize_contract_tracks_third_party_upstream(valid_regi'OpenMOSS-Team/MOSS-Transcribe-Diarize (third-party Apache-2.0 model)']assert entry['tested'] == {- 'funasr': 'ecosystem contract; third-party model@e8681d68',- 'runtime': 'vLLM 0.23.1rc1.dev949+g68b4a1d58 / Torch 2.11.0+cu129 / H100 80GB',+ 'funasr': 'AutoModel adapter@a3a2de0a; third-party model@e8681d68',+ 'runtime': 'Transformers 5.16.1 + vLLM 0.23.1rc1.dev949+g68b4a1d58 / Torch 2.11.0+cu129 / H100 80GB','verified': '2026-08-29',}@@ -125,6 +125,10 @@ def test_moss_transcribe_diarize_contract_tracks_third_party_upstream(valid_regiassert '/v1/audio/transcriptions' in smokeassert 'response_format=json' in smokeassert '[S01]' in smoke+ assert "from funasr import AutoModel" in smoke+ assert "backend='vllm'" in smoke+ assert "result['raw_text']" in smoke+ assert "result['sentence_info']" in smokeevidence_urls = {item['url'] for item in entry['evidence']}assert 'https://github.com/OpenMOSS/MOSS-Transcribe-Diarize' in evidence_urls@@ -136,13 +140,17 @@ def test_moss_transcribe_diarize_contract_tracks_third_party_upstream(valid_regi'https://huggingface.co/OpenMOSS-Team/MOSS-Transcribe-Diarize/tree/''e8681d68e7042738ffca8ac8212bc8fcb1131ab8') in evidence_urls+ assert 'https://github.com/modelscope/FunASR/pull/3558' in evidence_urlsenglish = entry['translations']['en']assert 'OpenMOSS' in english['summary']assert 'third-party' in english['summary'].lower()+ assert 'FunASR AutoModel' in english['summary']assert 'external VAD' in english['selection_reason']- assert 'verbose_json' in english['operations'][-1]- assert 'SGLang' in english['operations'][-1]+ assert 'FunASR AutoModel' in english['selection_reason']+ assert 'FunASR AutoModel API' not in ' '.join(english['not_fit'])+ assert 'sentence_info' in english['operations'][-1]+ assert 'raw_text' in english['operations'][-1]assert 'internal segmentation' in english['primary_limitation']assert 'FunASR model' in english['primary_limitation']assert any(