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(site): publish FunClip MOSS clipping guide
LauraGPT69b95c050e4b
diff --git a/web-pages/product-site/content/legacy-manifest.json b/web-pages/product-site/content/legacy-manifest.jsonindex 409843b05..1615cc60d 100644--- a/web-pages/product-site/content/legacy-manifest.json+++ b/web-pages/product-site/content/legacy-manifest.json@@ -21,8 +21,9 @@"blog/funasr-vs-faster-whisper-chinese.html": "bfe9bb8017be80c7e7f4587726f43f6064f1dc4c65e39788f836fdfb0c9789f7","blog/funasr-vs-whisper-benchmark.html": "b7b49adf24d20570abb09b733ce03d4a50a4a0e98e746b4a9320f453e01cce84","blog/funclip-v2-1-0-video-clipping-release.html": "88f6c44e5332d1746c4db0fc97d755ef82f12e46d8f1c1c0ad9351152ff9dfc1",+ "blog/funclip-v2-2-0-moss-speaker-clipping.html": "7127fb3d6493500d1e44e2168427b3e9adf9ec9bcd840d9da8fd5a1323af9709","blog/generate-subtitles-srt-vtt-from-audio-video.html": "f1133235673d441cc654310581f59a319f182314ab7c0b0824af87da9f4a0591",- "blog/index.html": "fbfa2611c97cc5426d78450078df36fb1818da1a5eeaef718e6a18fa9fd3d287",+ "blog/index.html": "0698ce3d08c4b61c1e1e3f94142d3564581d162765081437229d2c4f3fff5ff7","blog/japanese-speech-recognition.html": "399f5ce84e68ac00854bdf70b52b1cde6795efca7c800fd6492035a37a7c1b68","blog/lightweight-speech-recognition-cpu.html": "d6270066222ed5baef0df108e6a4155f4a87bb5482169f23f218794d371f3281","blog/punctuation-restoration-python.html": "6cd26e03bf75b4343afd7b351c2681ebd513b058fb549c5888802be9ff3a1229",@@ -59,8 +60,9 @@"en/blog/funasr-vs-faster-whisper-chinese.html": "abf31d3827dfba9b31ccd4e76229de9e4bfff00ab8bcee33bd718c88249630f4","en/blog/funasr-vs-whisper-benchmark.html": "367d4a8a1cc09ac932c80cdad065127925c5e5f942a806ace683c16dc1132769","en/blog/funclip-v2-1-0-video-clipping-release.html": "229baf59adf2c3290541d9b3c8a6243992406ba84b712714e9d14599205cb1d4",+ "en/blog/funclip-v2-2-0-moss-speaker-clipping.html": "6456c699b4837e5c1fc3741cda40a58a1d0caed8498351445e2dd6314dd89b3c","en/blog/generate-subtitles-srt-vtt-from-audio-video.html": "1530d4b9e94820a0b60d801e8d1c19b7aeb031b2f2b76c092657392e47706c6d",- "en/blog/index.html": "526253689a12ead8058ef9f45b9cdc37254f6507ab6d23511a742d88fddb95c2",+ "en/blog/index.html": "fc46e28078b49173d9f124afc51bed070b94b3738850b077a7fffcdaa965bc3a","en/blog/japanese-speech-recognition.html": "c476adcc2be1ed7c19e2345cc91b8ee6a0e04efd794b9b6476dd5d9b3a2c8b04","en/blog/lightweight-speech-recognition-cpu.html": "0e02c0e0853b12613d32c250f593c05c2052f18231207b63ee01d6e6600a86f7","en/blog/punctuation-restoration-python.html": "d6e30049f48d9dc6e6bc22eb567830013e4161eca51215616738b675dd1ffc40",@@ -106,7 +108,7 @@"models.html": "724c88917c9934ffa66948cf3eb583fed930dd689d691b7d21fa22ee8332e606","quickstart.html": "a543bf07c2cfc9a69ef3831f15c9e9d3e571a826a73cf7e4bdc8e9eb7b910254","robots.txt": "1305b0f680b3e9f73b01301dc474423230dffab85731a379a694f30c73c07f2d",- "sitemap.xml": "bcc17d763cd1b0d317b3af8e52cc40fde58c4a80f3fb5664a12b5503ecf2fc19",+ "sitemap.xml": "ed91fc0211b48458b77c56c1e600d055c013a6bb4b461821c3ec78dcff4ac26a","static/liveplayer/liveplayer-component.min.js": "ea10fda35574cc3a77a3e7187095467d1a409009a2d39690051d33d0e7055d30","static/liveplayer/liveplayer-lib.min.js": "ad67b4e1188c586ec218674a6db9968daf71ed4fbc262258f061c1f931d54250","static/offline/index.html": "868781c621ddabe5d3f088d6b739e0c08e6cdc150587af6515cc323852018e62",diff --git a/web-pages/product-site/data/deployments.json b/web-pages/product-site/data/deployments.jsonindex 873aa24e7..952c97497 100644--- a/web-pages/product-site/data/deployments.json+++ b/web-pages/product-site/data/deployments.json@@ -98,6 +98,8 @@{"label": "merged native SGLang Omni MOSS runtime and H100 benchmark", "url": "https://github.com/sgl-project/sglang-omni/pull/914"},{"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"},+ {"label": "FunClip v2.2.0 MOSS speaker-clipping guide", "url": "https://www.funasr.com/en/blog/funclip-v2-2-0-moss-speaker-clipping.html"},+ {"label": "FunClip v2.2.0 release and checksums", "url": "https://github.com/modelscope/FunClip/releases/tag/v2.2.0"},{"label": "moss-transcribe.cpp third-party C++17 and GGUF runtime", "url": "https://github.com/localai-org/moss-transcribe.cpp"},{"label": "LocalAI third-party moss-transcribe-cpp backend", "url": "https://github.com/mudler/LocalAI"}],diff --git a/web-pages/product-site/legacy/blog/funclip-v2-2-0-moss-speaker-clipping.html b/web-pages/product-site/legacy/blog/funclip-v2-2-0-moss-speaker-clipping.htmlnew file mode 100644index 000000000..fe29da7cc--- /dev/null+++ b/web-pages/product-site/legacy/blog/funclip-v2-2-0-moss-speaker-clipping.html@@ -0,0 +1,87 @@+<!DOCTYPE html>+<html lang="zh">+<head>+ <meta charset="utf-8">+ <meta name="viewport" content="width=device-width,initial-scale=1">+ <title>FunClip v2.2.0:MOSS 长音频说话人识别与视频剪辑 | FunASR</title>+ <meta name="description" content="FunClip v2.2.0 集成第三方 MOSS-Transcribe-Diarize,通过 vLLM 完成长音频 ASR、说话人分段、SRT 和按说话人剪辑。">+ <meta property="og:title" content="FunClip v2.2.0:MOSS 说话人识别与视频剪辑">+ <meta property="og:description" content="一条经过端到端验证的 vLLM 路径,输出说话人分段、SRT,并支持按说话人剪辑。">+ <meta property="og:type" content="article">+ <meta property="og:url" content="https://www.funasr.com/blog/funclip-v2-2-0-moss-speaker-clipping.html">+ <meta property="og:image" content="https://www.funasr.com/img/funclip-v2-1-0-interface.jpg">+ <link rel="canonical" href="https://www.funasr.com/blog/funclip-v2-2-0-moss-speaker-clipping.html">+ <link rel="alternate" hreflang="en" href="https://www.funasr.com/en/blog/funclip-v2-2-0-moss-speaker-clipping.html">+ <link rel="alternate" hreflang="zh" href="https://www.funasr.com/blog/funclip-v2-2-0-moss-speaker-clipping.html">+ <link rel="alternate" hreflang="x-default" href="https://www.funasr.com/en/blog/funclip-v2-2-0-moss-speaker-clipping.html">+ <script type="application/ld+json">{"@context":"https://schema.org","@type":"BlogPosting","headline":"FunClip v2.2.0:MOSS 长音频说话人识别与视频剪辑","datePublished":"2026-08-31","dateModified":"2026-08-31","author":{"@type":"Organization","name":"FunASR / Tongyi Lab"},"publisher":{"@type":"Organization","name":"FunASR"},"mainEntityOfPage":{"@type":"WebPage","@id":"https://www.funasr.com/blog/funclip-v2-2-0-moss-speaker-clipping.html"},"image":"https://www.funasr.com/img/funclip-v2-1-0-interface.jpg"}</script>+ <style>+ p code,li code,td code,.proof code{overflow-wrap:anywhere}+ :root{--primary:#2563eb;--accent:#047857;--surface:#f8fafc;--border:#dbe3ec;--text:#0f172a;--soft:#475569}+ *{box-sizing:border-box}body{margin:0;font-family:Inter,-apple-system,BlinkMacSystemFont,"Segoe UI",sans-serif;color:var(--text);line-height:1.72;background:#fff}a{color:var(--primary);text-decoration:none}a:hover{text-decoration:underline}.container{max-width:840px;margin:auto;padding:0 24px}.nav{position:sticky;top:0;z-index:10;background:#fff;border-bottom:1px solid var(--border);padding:14px 0}.nav .container{max-width:1120px;display:flex;align-items:center;gap:20px}.nav-logo{font-weight:800;color:var(--text)}.nav-logo span{color:var(--primary)}.nav-links{display:flex;gap:16px;margin-left:auto}.nav-btn{padding:8px 14px;background:var(--primary);color:#fff;border-radius:7px}article{padding:64px 0 80px}h1{font-size:2.1rem;line-height:1.28;margin:0 0 12px}h2{font-size:1.35rem;margin:36px 0 12px;padding-top:20px;border-top:1px solid var(--border)}p,li{color:var(--soft)}.meta{color:#64748b}.lead{font-size:1.08rem;color:var(--text)}.hero-media{width:100%;aspect-ratio:2.04/1;object-fit:cover;border:1px solid var(--border);border-radius:8px;margin:18px 0 24px}pre{overflow:auto;background:#172033;color:#e2e8f0;padding:18px;border-radius:8px;line-height:1.6}code{font-family:ui-monospace,SFMono-Regular,Menlo,monospace}p code,li code,td code{background:var(--surface);padding:2px 5px;border-radius:4px;color:#1d4ed8}table{width:100%;border-collapse:collapse;margin:18px 0}th,td{text-align:left;vertical-align:top;padding:11px;border-bottom:1px solid var(--border)}th{background:var(--surface)}.proof{border-left:4px solid var(--accent);background:#f0fdf4;padding:14px 16px;color:#14532d}.cta{margin-top:30px;padding:22px;border:1px solid var(--border);border-radius:8px}.cta a{font-weight:700}footer{padding:28px;background:#0f172a;color:#94a3b8;text-align:center}@media(max-width:800px){.nav-links{display:none}h1{font-size:1.65rem}}+ </style>+</head>+<body>+<nav class="nav"><div class="container"><a class="nav-logo" href="/">Fun<span>ASR</span></a><div class="nav-links"><a href="/deploy/">部署</a><a href="/blog/">博客</a><a href="/ecosystem.html">生态</a></div><a href="/en/blog/funclip-v2-2-0-moss-speaker-clipping.html">EN</a><a class="nav-btn" href="https://github.com/modelscope/FunASR">GitHub</a></div></nav>+<article><div class="container">+ <h1>FunClip v2.2.0:用 MOSS 做长音频说话人识别与视频剪辑</h1>+ <p class="meta">2026-08-31 · FunClip Release</p>+ <img class="hero-media" src="/img/funclip-v2-1-0-interface.jpg" alt="FunClip 本地视频、字幕识别和智能剪辑界面">+ <p class="lead">FunClip v2.2.0 新增一条可选的 MOSS 路径:把长音频交给 vLLM 服务,FunASR 将模型输出归一化为文本、说话人身份和时间段,FunClip 再生成 SRT 或按 <code>spkS01</code>、<code>spkS02</code> 剪辑。</p>+ <p><a href="https://github.com/OpenMOSS/MOSS-Transcribe-Diarize">MOSS-Transcribe-Diarize</a> 是 OpenMOSS 维护的第三方模型,不属于 FunASR 或 FunClip。集成固定使用 <code>OpenMOSS-Team/MOSS-Transcribe-Diarize</code> revision <code>e8681d68e7042738ffca8ac8212bc8fcb1131ab8</code>,并明确保留模型归属与支持边界。</p>++ <h2>数据路径</h2>+ <table><thead><tr><th>阶段</th><th>职责</th></tr></thead><tbody>+ <tr><td>vLLM</td><td>加载固定 MOSS revision,通过 <code>/v1/audio/transcriptions</code> 返回带时间与说话人标记的 JSON。</td></tr>+ <tr><td>FunASR 1.4.9+</td><td>解析转写结果并生成统一的 <code>text</code>、<code>timestamp</code> 与 <code>sentence_info</code>。</td></tr>+ <tr><td>FunClip 2.2.0</td><td>渲染说话人 SRT、按说话人选段,或把时间段交给现有音视频剪辑流程。</td></tr>+ </tbody></table>++ <h2>1. 启动固定 revision 的 vLLM 服务</h2>+ <pre><code>python -m venv .venv-moss+. .venv-moss/bin/activate+pip install -U vllm++vllm serve OpenMOSS-Team/MOSS-Transcribe-Diarize \+ --revision e8681d68e7042738ffca8ac8212bc8fcb1131ab8 \+ --served-model-name moss-transcribe-diarize \+ --trust-remote-code --host 127.0.0.1 --port 8898</code></pre>+ <p>先用真实音频检查服务契约。当前经过验证的格式是 <code>response_format=json</code>:</p>+ <pre><code>curl -fsS http://127.0.0.1:8898/v1/audio/transcriptions \+ -F [email protected] \+ -F model=moss-transcribe-diarize \+ -F response_format=json \+ -F max_completion_tokens=8192</code></pre>++ <h2>2. 启动 FunClip</h2>+ <pre><code>python -m pip install -U -r requirements.txt+python funclip/launch.py \+ --model moss \+ --moss-backend vllm \+ --moss-base-url http://127.0.0.1:8898/v1 \+ --moss-max-tokens 8192</code></pre>+ <p>远端服务需要 bearer token 时,把凭据放进 <code>MOSS_API_KEY</code> 环境变量;FunClip 不要求把 token 写进命令行或仓库。</p>++ <h2>能力与边界</h2>+ <ul>+ <li>支持长音频 ASR、说话人身份、SRT,以及按说话人剪辑,包括不足一秒的有效短说话片段。</li>+ <li>MOSS 提供段级时间戳,适合按整段或说话人剪辑;任意文本的精确字符级剪辑仍应使用 Paraformer。</li>+ <li>全局说话人身份依赖模型看到连续音频,因此不接外部 VAD 或说话人模型,避免预切块破坏身份一致性。</li>+ <li>如果最后一个 MOSS 片段因 token 上限没有结束时间戳,FunClip 会明确报错并提示提高 <code>--moss-max-tokens</code>,不会静默丢掉尾段。</li>+ </ul>+ <p>完整生产部署、健康检查和容量边界见 <a href="/deploy/moss-transcribe-diarize.html">MOSS 双语部署指南</a>。</p>++ <h2>下载与校验 v2.2.0</h2>+ <pre><code>FunClip-2.2.0.tar.gz+SHA256 994c5d9cf392b74b36284d526eca8bada1560a3e7825ab7baa9c673a1b4ef216++FunClip-2.2.0.zip+SHA256 4f5a7d33d9ea65467f29b55b15ed5be18e64de7e57e2f9f36fe51a23b40557e7</code></pre>+ <p>从 <a href="https://github.com/modelscope/FunClip/releases/tag/v2.2.0">FunClip v2.2.0 Release</a> 下载归档和 <code>SHA256SUMS</code>,不要从不明镜像复制二进制或凭据。</p>++ <div class="proof">发布内容对应 commit <code>c205bf32a8b11226ff5e8acb9a3c7a1f00cd3b06</code>。仓库测试结果为 84 passed、1 skipped;H100 + vLLM 两说话人样例返回 S01/S02、有效 SRT,并成功按 S02 剪辑。这个验证证明发布链路可用,不代表所有语言、音频条件或并发规模。</div>+ <div class="cta"><p>先按部署指南跑通一段真实双人音频,再进入 FunClip 处理自己的视频。</p><a href="https://github.com/modelscope/FunClip/releases/tag/v2.2.0">查看 FunClip v2.2.0 发布与下载</a></div>+</div></article>+<footer>© 2024-2026 Tongyi Lab, Alibaba Group</footer>+</body>+</html>diff --git a/web-pages/product-site/legacy/blog/index.html b/web-pages/product-site/legacy/blog/index.htmlindex 7925da337..9627c3f37 100644--- a/web-pages/product-site/legacy/blog/index.html+++ b/web-pages/product-site/legacy/blog/index.html@@ -42,13 +42,13 @@ p code,li code{background:var(--surface);padding:2px 6px;border-radius:5px;font-.post-card p{margin:0;color:var(--text-soft);font-size:0.9rem}.post-card .date{color:var(--text-muted);font-size:0.8rem}.launch-feature{max-width:800px;margin:104px auto 0;padding:0 24px}.launch-feature a{display:grid;grid-template-columns:1fr auto;align-items:center;gap:20px;border:1px solid #bbf7d0;border-left:4px solid #047857;border-radius:8px;background:#f0fdf4;padding:20px 22px;color:var(--text)}.launch-feature a:hover{border-color:#047857;text-decoration:none}.launch-feature .date{font-size:.8rem;color:#047857;font-weight:600}.launch-feature h2{border:0;padding:0;margin:3px 0 5px;font-size:1.2rem}.launch-feature p{margin:0;font-size:.9rem}.launch-feature .action{font-weight:700;color:#1d4ed8;white-space:nowrap}-.previous-release{padding-top:16px}.previous-release .container{display:grid;grid-template-columns:repeat(3,minmax(0,1fr));gap:16px}.previous-release .post-card{margin-bottom:0}+.previous-release{padding-top:16px}.previous-release .container{display:grid;grid-template-columns:repeat(4,minmax(0,1fr));gap:16px}.previous-release .post-card{margin-bottom:0}footer{background:#0f172a;color:#94a3b8;padding:28px 0;text-align:center;font-size:0.8rem}footer a{color:#94a3b8}@media(max-width:900px){.nav-links{display:none}.nav .container{gap:16px}.nav-logo{margin-right:auto}.launch-feature a{grid-template-columns:1fr}.launch-feature .action{white-space:normal}.previous-release .container{grid-template-columns:1fr}}</style></head><body><nav class="nav"><div class="container"><a href="/" class="nav-logo">Fun<span>ASR</span></a><div class="nav-links"><a href="/#capabilities">核心能力</a><a href="/#usage">如何使用</a><a href="/#benchmark">性能</a><a href="/#demo">演示</a><a href="https://modelscope.github.io/FunASR/zh/" target="_blank">文档</a><a href="/quickstart.html">快速上手</a><a href="/models.html">模型</a><a href="/ecosystem.html">生态</a><a href="/blog/">技术博客</a><a href="/vs-whisper.html">对比 Whisper</a><a href="/donors.html">功德榜</a></div><a href="https://www.funasr.com/en/blog/" style="font-size:0.83rem;font-weight:500;color:var(--text-soft)">EN</a><a href="/go/github" target="_blank" class="nav-btn">GitHub ★</a></div></nav>-<section class="launch-feature"><a href="/blog/funasr-v1-4-5-pypi-llama-cpp-release.html"><div><span class="date">2026-08-28 · 正式 Release</span><h2>FunASR v1.4.5:更轻的 Python 推理与九平台 llama.cpp 运行时</h2><p>默认安装不再硬依赖 torchaudio,可选 kaldi-native-fbank,并在一个页面提供 PyPI 包、九平台运行时与 SHA-256 清单。</p></div><span class="action">查看安装与部署指南 →</span></a></section>-<section class="previous-release"><div class="container"><a class="post-card" href="/blog/funasr-v1-4-3-pypi-release.html"><span class="date">2026-08-21 · 正式 Release</span><h2>FunASR v1.4.3:可选 Silero VAD 与大规模固定 K 说话人聚类</h2><p>新增毫秒级 Silero VAD 适配器,降低已知说话人数的大规模聚类内存压力,并提供 12 个带 SHA-256 的发布资产。</p></a><a class="post-card" href="/blog/funasr-v1-4-0-pypi-release.html"><span class="date">2026-07-31 · 正式 Release</span><h2>FunASR v1.4.0:更完整的 PyPI 安装包与更安全的 AutoModel 参数</h2><p>修复 SenseVoice 与 RWKV-BAT 包数据,提前拒绝 vda_model 误拼写,并提供 12 个带 SHA-256 的发布资产。</p></a><a class="post-card" href="/blog/subtitle-edit-fun-asr-sensevoice-local-subtitles.html"><span class="date">2026-08-03 · 生态集成</span><h2>Subtitle Edit 5.2:Fun-ASR Nano / SenseVoice 本地视频字幕</h2><p>在 Windows、macOS 与 Linux 的成熟字幕工作区中直接选择本地 ASR 引擎,支持 Q4、Q8、F16。</p></a></div></section>+<section class="launch-feature"><a href="/blog/funclip-v2-2-0-moss-speaker-clipping.html"><div><span class="date">2026-08-31 · FunClip v2.2.0</span><h2>MOSS 多说话人转写进入 FunClip:从一句话到带说话人的片段</h2><p>通过经真实双说话人音频验证的 vLLM 路径,把第三方 MOSS 模型的段级时间戳和说话人标签直接用于 SRT 与说话人片段导出。</p></div><span class="action">查看部署与剪辑边界 →</span></a></section>+<section class="previous-release"><div class="container"><a class="post-card" href="/blog/funasr-v1-4-5-pypi-llama-cpp-release.html"><span class="date">2026-08-28 · 正式 Release</span><h2>FunASR v1.4.5:更轻的 Python 推理与九平台 llama.cpp 运行时</h2><p>默认安装不再硬依赖 torchaudio,可选 kaldi-native-fbank,并提供 PyPI 包、九平台运行时与 SHA-256 清单。</p></a><a class="post-card" href="/blog/funasr-v1-4-3-pypi-release.html"><span class="date">2026-08-21 · 正式 Release</span><h2>FunASR v1.4.3:可选 Silero VAD 与大规模固定 K 说话人聚类</h2><p>新增毫秒级 Silero VAD 适配器,降低已知说话人数的大规模聚类内存压力,并提供 12 个带 SHA-256 的发布资产。</p></a><a class="post-card" href="/blog/funasr-v1-4-0-pypi-release.html"><span class="date">2026-07-31 · 正式 Release</span><h2>FunASR v1.4.0:更完整的 PyPI 安装包与更安全的 AutoModel 参数</h2><p>修复 SenseVoice 与 RWKV-BAT 包数据,提前拒绝 vda_model 误拼写,并提供 12 个带 SHA-256 的发布资产。</p></a><a class="post-card" href="/blog/subtitle-edit-fun-asr-sensevoice-local-subtitles.html"><span class="date">2026-08-03 · 生态集成</span><h2>Subtitle Edit 5.2:Fun-ASR Nano / SenseVoice 本地视频字幕</h2><p>在 Windows、macOS 与 Linux 的成熟字幕工作区中直接选择本地 ASR 引擎,支持 Q4、Q8、F16。</p></a></div></section><article><div class="container"><h1>FunASR 技术博客</h1><p class="post-meta">语音识别部署、教程与最佳实践</p><a class="post-card" href="/blog/speech-to-text-timestamps-python.html"><span class="date">2026-06-23</span><h2>语音识别带时间戳(字级 timestamps)Python 实战:每个字精确到毫秒</h2><p>FunASR Paraformer 原生字级时间戳:每个字带 [起始毫秒,结束毫秒],一次调用即有。可做逐字高亮、点击跳转、字幕对齐。附真实实测+配对代码。</p></a><a class="post-card" href="/blog/punctuation-restoration-python.html"><span class="date">2026-06-23</span><h2>标点恢复 Python 实战:给无标点文本/ASR 结果自动加标点</h2><p>FunASR ct-punc 开源标点恢复,中英双语,3 行 Python 补全 ,。?(英文还做句首大写),也能一行挂到 ASR 上。附真实实测。</p></a><a class="post-card" href="/blog/chinese-speech-recognition.html"><span class="date">2026-06-22</span><h2>中文语音识别(普通话)Python 实战:用 FunASR 又快又准</h2><p>FunASR 专为中文打造:默认旗舰 Fun-ASR-Nano(CER 8.06%),CPU 用 SenseVoice(7.81%)/ Paraformer(10.18%,时间戳/热词),都远好于 Whisper(~20%)。3 行 Python。</p></a><a class="post-card" href="/blog/self-hosted-google-aws-azure-speech-to-text.html"><span class="date">2026-06-22</span><h2>自托管语音转文字:Google / AWS / Azure 云语音 API 的免费开源替代</h2><p>开源免费(MIT)、本地推理、不按分钟计费、数据不出内网、中文强,OpenAI 兼容改 base_url 即可迁移。附实测代码 + FunASR vs 云 API 对比 + 成本分析。</p></a><a class="post-card" href="/blog/voice-activity-detection-python.html"><span class="date">2026-06-22</span><h2>Python 语音活动检测(VAD):检测语音、去静音、按停顿切分音频</h2><p>FunASR fsmn-vad 3 行代码返回每段语音的起止毫秒。实测 13s 录音 0.12s 切成 2 段、去除 18% 静音;可去静音、切分长录音、给 Whisper 等做预处理防幻觉。</p></a><a class="post-card" href="/blog/japanese-speech-recognition.html"><span class="date">2026-06-22</span><h2>日语语音识别:SenseVoice 一个模型搞定日语转写+标点+情感</h2><p>同一段日语音频实测:SenseVoice 写对同音字 転売、自动加标点,Whisper-small 误为 天売、无标点。原生 ja 支持 + 自动语种识别 + 情感事件,3 行 Python。</p></a><a class="post-card" href="/blog/self-hosted-deepgram-assemblyai-alternative.html"><span class="date">2026-06-23</span><h2>自托管替代 Deepgram / AssemblyAI</h2><p>开源免费、自托管、音频不出本地、中文领先,自带 OpenAI 兼容 API——客户端只改 base_url 即可替代按分钟付费的云 STT。</p></a><a class="post-card" href="/blog/which-funasr-model.html"><span class="date">2026-06-23</span><h2>选哪个 FunASR 模型?Nano vs MLT-Nano vs SenseVoice vs Paraformer</h2><p>模型选型表 + 场景代码:中英日及中文方言/口音选旗舰 Nano,31 语种选独立 MLT-Nano,CPU 再选 SenseVoice 或 Paraformer。</p></a><a class="post-card" href="/blog/lightweight-speech-recognition-cpu.html"><span class="date">2026-06-22</span><h2>轻量语音识别:CPU 上约 250MB 跑中文 ASR</h2><p>单二进制 + 254MB q8 模型,无需 GPU/Python,CPU 0.16s,中文 CER 7.99%——比 whisper.cpp small 还小且准 3 倍。</p></a><a class="post-card" href="/blog/cantonese-speech-recognition.html"><span class="date">2026-06-21</span><h2>粤语语音识别:SenseVoice 原生支持粤语口语(Whisper 会转成普通话)</h2><p>同一段粤语音频实测:SenseVoice 保留 呢/唔/嘅,Whisper 转成普通话书面语。原生 yue 支持 + 自动语种识别,3 行 Python。</p></a><a class="post-card" href="/blog/funasr-vs-faster-whisper-chinese.html"><span class="date">2026-06-21</span><h2>FunASR vs faster-whisper:中文与粤语实测对比</h2><p>粤语被 faster-whisper 误判为普通话、日语同音字错;SenseVoice 原生支持粤语+语种识别,中文 CER 低约 2.7 倍。实测。</p></a><a class="post-card" href="/blog/funasr-llama-cpp-whisper-cpp-alternative.html"><span class="date">2026-06-20</span><h2>FunASR 跑进 llama.cpp:中文 ASR 的 whisper.cpp 替代品(CPU/零 Python)</h2><p>单个自包含二进制、内置 VAD、吃任意音频,下载即用转写中文;中文 CPU 上比 whisper.cpp 准约 2.7 倍。3 步实测。</p></a><a class="post-card" href="/blog/speech-to-text-python-transcribe-audio.html"><span class="date">2026-06-18</span><h2>Python 语音转文字:用 FunASR 本地免费转写音频</h2><p>几行 Python 把音频转成文本,带时间戳/说话人/批量;本地、免费、无 API key、中文强。</p></a><a class="post-card" href="/blog/generate-subtitles-srt-vtt-from-audio-video.html"><span class="date">2026-06-18</span><h2>用 FunASR 自动生成字幕:音频/视频一键出 SRT 和 VTT</h2><p>一行命令出 SRT,Python 同时导出 VTT,带说话人和真实时间戳;本地、免费、中文强。</p></a><a class="post-card" href="/blog/self-hosted-openai-whisper-api-alternative.html"><span class="date">2026-06-18</span><h2>自托管 OpenAI Whisper API 替代:FunASR 起兼容 /v1/audio/transcriptions 服务</h2><p>funasr-server 暴露 OpenAI 兼容接口,OpenAI SDK 只改 base_url 就能用;本地、免费、隐私、中文更准。</p></a><a class="post-card" href="/blog/funasr-cli-transcribe-command-line.html"><span class="date">2026-06-18</span><h2>用 FunASR 命令行转写音频:文本/JSON/SRT 字幕</h2><p>一行命令出文字/字幕/JSON,--spk 带说话人;还能 funasr-server 起 OpenAI 兼容 API。</p></a><a class="post-card" href="/blog/funasr-transcribe-long-audio.html"><span class="date">2026-06-17</span><h2>用 FunASR 转写超长音频:1 小时一次搞定</h2><p>Whisper 限 30 秒,FunASR 内置 VAD 一次吃下任意时长;实测 13 分钟 4.3 秒转完(186x)。</p></a><a class="post-card" href="/blog/funasr-realtime-streaming-asr.html"><span class="date">2026-06-17</span><h2>用 FunASR 实现实时流式语音识别(边说边出字)</h2><p>600ms 级低延迟流式 ASR:分块+cache 边说边出字,含 2-pass(流式+离线)最佳实践。</p></a><a class="post-card" href="/blog/sensevoice-emotion-language-detection.html"><span class="date">2026-06-17</span><h2>超越转写:用 SenseVoice 识别语言、情感与声学事件</h2><p>一次非自回归前向同时输出转写+语种+情感+音频事件,Whisper 做不到的四合一。</p></a><a class="post-card" href="/blog/funasr-speaker-diarization.html"><span class="date">2026-06-17</span><h2>用 FunASR 做说话人分离:谁在何时说了什么</h2><p>一次 generate 调用同时输出转写+说话人标签+时间戳,替代 pyannote+Whisper,无需 HF 授权。</p></a><a class="post-card" href="/blog/funasr-vs-whisper-benchmark.html"><span class="date">2026-06-16</span><h2>FunASR vs Whisper 实测对比:谁更快更准</h2><p>184 中文文件 H100 实测:SenseVoice 169.6x、CER 7.81%,完整速度+准确率数据。</p></a><a class="post-card" href="/blog/fun-asr-nano-guide.html"><span class="date">2026-06-16</span><h2>Fun-ASR-Nano 使用指南:800M 端到端语音识别大模型</h2><p>主力旗舰,中英日 + 7 大中文方言/26 种口音,热词/流式/说话人分离;31 语种请用 MLT-Nano。</p></a><a class="post-card" href="/blog/sensevoice-deployment-guide.html"><span class="date">2026-06-16</span><h2>SenseVoice 部署指南:五语种识别、情感与音频事件</h2><p>3 行代码跑通多语言识别,含语种/情感/事件检测、VAD、GPU/CPU。</p></a><p>更多:<a href="/quickstart.html">快速上手</a> · <a href="/models.html">模型</a></p></div></article><footer><div class="container">© 2024-2026 Tongyi Lab, Alibaba Group · <a href="https://github.com/modelscope/FunASR/blob/main/LICENSE">MIT License</a></div></footer></body></html>diff --git a/web-pages/product-site/legacy/en/blog/funclip-v2-2-0-moss-speaker-clipping.html b/web-pages/product-site/legacy/en/blog/funclip-v2-2-0-moss-speaker-clipping.htmlnew file mode 100644index 000000000..b19deb146--- /dev/null+++ b/web-pages/product-site/legacy/en/blog/funclip-v2-2-0-moss-speaker-clipping.html@@ -0,0 +1,87 @@+<!DOCTYPE html>+<html lang="en">+<head>+ <meta charset="utf-8">+ <meta name="viewport" content="width=device-width,initial-scale=1">+ <title>FunClip v2.2.0: MOSS Speaker-Aware Video Clipping | FunASR</title>+ <meta name="description" content="FunClip v2.2.0 integrates the third-party MOSS-Transcribe-Diarize model through vLLM for long-form ASR, speaker segments, SRT, and speaker-based clipping.">+ <meta property="og:title" content="FunClip v2.2.0: MOSS Speaker-Aware Video Clipping">+ <meta property="og:description" content="An end-to-end tested vLLM path for speaker segments, SRT, and speaker-based video clipping.">+ <meta property="og:type" content="article">+ <meta property="og:url" content="https://www.funasr.com/en/blog/funclip-v2-2-0-moss-speaker-clipping.html">+ <meta property="og:image" content="https://www.funasr.com/img/funclip-v2-1-0-interface.jpg">+ <link rel="canonical" href="https://www.funasr.com/en/blog/funclip-v2-2-0-moss-speaker-clipping.html">+ <link rel="alternate" hreflang="en" href="https://www.funasr.com/en/blog/funclip-v2-2-0-moss-speaker-clipping.html">+ <link rel="alternate" hreflang="zh" href="https://www.funasr.com/blog/funclip-v2-2-0-moss-speaker-clipping.html">+ <link rel="alternate" hreflang="x-default" href="https://www.funasr.com/en/blog/funclip-v2-2-0-moss-speaker-clipping.html">+ <script type="application/ld+json">{"@context":"https://schema.org","@type":"BlogPosting","headline":"FunClip v2.2.0: MOSS Speaker-Aware Video Clipping","datePublished":"2026-08-31","dateModified":"2026-08-31","author":{"@type":"Organization","name":"FunASR / Tongyi Lab"},"publisher":{"@type":"Organization","name":"FunASR"},"mainEntityOfPage":{"@type":"WebPage","@id":"https://www.funasr.com/en/blog/funclip-v2-2-0-moss-speaker-clipping.html"},"image":"https://www.funasr.com/img/funclip-v2-1-0-interface.jpg"}</script>+ <style>+ p code,li code,td code,.proof code{overflow-wrap:anywhere}+ :root{--primary:#2563eb;--accent:#047857;--surface:#f8fafc;--border:#dbe3ec;--text:#0f172a;--soft:#475569}+ *{box-sizing:border-box}body{margin:0;font-family:Inter,-apple-system,BlinkMacSystemFont,"Segoe UI",sans-serif;color:var(--text);line-height:1.72;background:#fff}a{color:var(--primary);text-decoration:none}a:hover{text-decoration:underline}.container{max-width:840px;margin:auto;padding:0 24px}.nav{position:sticky;top:0;z-index:10;background:#fff;border-bottom:1px solid var(--border);padding:14px 0}.nav .container{max-width:1120px;display:flex;align-items:center;gap:20px}.nav-logo{font-weight:800;color:var(--text)}.nav-logo span{color:var(--primary)}.nav-links{display:flex;gap:16px;margin-left:auto}.nav-btn{padding:8px 14px;background:var(--primary);color:#fff;border-radius:7px}article{padding:64px 0 80px}h1{font-size:2.1rem;line-height:1.28;margin:0 0 12px}h2{font-size:1.35rem;margin:36px 0 12px;padding-top:20px;border-top:1px solid var(--border)}p,li{color:var(--soft)}.meta{color:#64748b}.lead{font-size:1.08rem;color:var(--text)}.hero-media{width:100%;aspect-ratio:2.04/1;object-fit:cover;border:1px solid var(--border);border-radius:8px;margin:18px 0 24px}pre{overflow:auto;background:#172033;color:#e2e8f0;padding:18px;border-radius:8px;line-height:1.6}code{font-family:ui-monospace,SFMono-Regular,Menlo,monospace}p code,li code,td code{background:var(--surface);padding:2px 5px;border-radius:4px;color:#1d4ed8}table{width:100%;border-collapse:collapse;margin:18px 0}th,td{text-align:left;vertical-align:top;padding:11px;border-bottom:1px solid var(--border)}th{background:var(--surface)}.proof{border-left:4px solid var(--accent);background:#f0fdf4;padding:14px 16px;color:#14532d}.cta{margin-top:30px;padding:22px;border:1px solid var(--border);border-radius:8px}.cta a{font-weight:700}footer{padding:28px;background:#0f172a;color:#94a3b8;text-align:center}@media(max-width:800px){.nav-links{display:none}h1{font-size:1.65rem}}+ </style>+</head>+<body>+<nav class="nav"><div class="container"><a class="nav-logo" href="/en/">Fun<span>ASR</span></a><div class="nav-links"><a href="/en/deploy/">Deploy</a><a href="/en/blog/">Blog</a><a href="/en/ecosystem.html">Ecosystem</a></div><a href="/blog/funclip-v2-2-0-moss-speaker-clipping.html">中文</a><a class="nav-btn" href="https://github.com/modelscope/FunASR">GitHub</a></div></nav>+<article><div class="container">+ <h1>FunClip v2.2.0: Long-Form Speaker-Aware Video Clipping with MOSS</h1>+ <p class="meta">August 31, 2026 · FunClip Release</p>+ <img class="hero-media" src="/img/funclip-v2-1-0-interface.jpg" alt="FunClip local video, subtitle recognition, and intelligent clipping interface">+ <p class="lead">FunClip v2.2.0 adds an opt-in MOSS path: send long audio to a vLLM service, normalize text, speaker identities, and time ranges through FunASR, then generate SRT or clip by <code>spkS01</code>, <code>spkS02</code>, and later speaker IDs.</p>+ <p><a href="https://github.com/OpenMOSS/MOSS-Transcribe-Diarize">MOSS-Transcribe-Diarize</a> is a third-party model maintained by OpenMOSS, not a FunASR or FunClip-owned checkpoint. The integration pins <code>OpenMOSS-Team/MOSS-Transcribe-Diarize</code> revision <code>e8681d68e7042738ffca8ac8212bc8fcb1131ab8</code> and keeps ownership and support boundaries explicit.</p>++ <h2>Data path</h2>+ <table><thead><tr><th>Stage</th><th>Responsibility</th></tr></thead><tbody>+ <tr><td>vLLM</td><td>Loads the pinned MOSS revision and serves timestamped speaker markup through <code>/v1/audio/transcriptions</code>.</td></tr>+ <tr><td>FunASR 1.4.9+</td><td>Parses the response into common <code>text</code>, <code>timestamp</code>, and <code>sentence_info</code> fields.</td></tr>+ <tr><td>FunClip 2.2.0</td><td>Renders speaker-labeled SRT and sends selected speaker ranges into the existing audio/video clipping workflow.</td></tr>+ </tbody></table>++ <h2>1. Start vLLM at the pinned revision</h2>+ <pre><code>python -m venv .venv-moss+. .venv-moss/bin/activate+pip install -U vllm++vllm serve OpenMOSS-Team/MOSS-Transcribe-Diarize \+ --revision e8681d68e7042738ffca8ac8212bc8fcb1131ab8 \+ --served-model-name moss-transcribe-diarize \+ --trust-remote-code --host 127.0.0.1 --port 8898</code></pre>+ <p>Verify the service with real audio before starting FunClip. The tested contract uses <code>response_format=json</code>:</p>+ <pre><code>curl -fsS http://127.0.0.1:8898/v1/audio/transcriptions \+ -F [email protected] \+ -F model=moss-transcribe-diarize \+ -F response_format=json \+ -F max_completion_tokens=8192</code></pre>++ <h2>2. Start FunClip</h2>+ <pre><code>python -m pip install -U -r requirements.txt+python funclip/launch.py \+ --model moss \+ --moss-backend vllm \+ --moss-base-url http://127.0.0.1:8898/v1 \+ --moss-max-tokens 8192</code></pre>+ <p>For an authenticated remote service, put the bearer credential in the <code>MOSS_API_KEY</code> environment variable. FunClip does not require putting the token in the command line or repository.</p>++ <h2>Capabilities and boundaries</h2>+ <ul>+ <li>Long-form ASR, speaker identity, SRT, and speaker-based clipping are supported, including valid speaker turns shorter than one second.</li>+ <li>MOSS provides segment-level timestamps. Use it for whole-segment or speaker clipping; keep Paraformer for precise arbitrary character-level text clipping.</li>+ <li>Global speaker identity depends on continuous context, so the MOSS path attaches no external VAD or speaker model that would pre-chunk the recording.</li>+ <li>If the final segment is missing its ending timestamp after token exhaustion, FunClip raises an explicit truncation error and asks for a higher <code>--moss-max-tokens</code> value instead of silently dropping the tail.</li>+ </ul>+ <p>See the <a href="/en/deploy/moss-transcribe-diarize.html">bilingual MOSS production guide</a> for health checks, runtime choices, and capacity boundaries.</p>++ <h2>Download and verify v2.2.0</h2>+ <pre><code>FunClip-2.2.0.tar.gz+SHA256 994c5d9cf392b74b36284d526eca8bada1560a3e7825ab7baa9c673a1b4ef216++FunClip-2.2.0.zip+SHA256 4f5a7d33d9ea65467f29b55b15ed5be18e64de7e57e2f9f36fe51a23b40557e7</code></pre>+ <p>Download the archives and <code>SHA256SUMS</code> from the <a href="https://github.com/modelscope/FunClip/releases/tag/v2.2.0">FunClip v2.2.0 release</a>.</p>++ <div class="proof">Release content resolves to commit <code>c205bf32a8b11226ff5e8acb9a3c7a1f00cd3b06</code>. The repository suite completed with 84 passed and 1 skipped. A live H100 + vLLM two-speaker run returned S01/S02, valid SRT, and the expected S02 clip. This verifies the release path, not every language, audio condition, or production concurrency level.</div>+ <div class="cta"><p>Run one real two-speaker recording through the production guide, then bring the same service into FunClip.</p><a href="https://github.com/modelscope/FunClip/releases/tag/v2.2.0">Open the FunClip v2.2.0 release and downloads</a></div>+</div></article>+<footer>© 2024-2026 Tongyi Lab, Alibaba Group</footer>+</body>+</html>diff --git a/web-pages/product-site/legacy/en/blog/index.html b/web-pages/product-site/legacy/en/blog/index.htmlindex fe315c379..2191d5a2b 100644--- a/web-pages/product-site/legacy/en/blog/index.html+++ b/web-pages/product-site/legacy/en/blog/index.html@@ -42,13 +42,13 @@ p code,li code{background:var(--surface);padding:2px 6px;border-radius:5px;font-.post-card p{margin:0;color:var(--text-soft);font-size:0.9rem}.post-card .date{color:var(--text-muted);font-size:0.8rem}.launch-feature{max-width:800px;margin:104px auto 0;padding:0 24px}.launch-feature a{display:grid;grid-template-columns:1fr auto;align-items:center;gap:20px;border:1px solid #bbf7d0;border-left:4px solid #047857;border-radius:8px;background:#f0fdf4;padding:20px 22px;color:var(--text)}.launch-feature a:hover{border-color:#047857;text-decoration:none}.launch-feature .date{font-size:.8rem;color:#047857;font-weight:600}.launch-feature h2{border:0;padding:0;margin:3px 0 5px;font-size:1.2rem}.launch-feature p{margin:0;font-size:.9rem}.launch-feature .action{font-weight:700;color:#1d4ed8;white-space:nowrap}-.previous-release{padding-top:16px}.previous-release .container{display:grid;grid-template-columns:repeat(3,minmax(0,1fr));gap:16px}.previous-release .post-card{margin-bottom:0}+.previous-release{padding-top:16px}.previous-release .container{display:grid;grid-template-columns:repeat(4,minmax(0,1fr));gap:16px}.previous-release .post-card{margin-bottom:0}footer{background:#0f172a;color:#94a3b8;padding:28px 0;text-align:center;font-size:0.8rem}footer a{color:#94a3b8}@media(max-width:900px){.nav-links{display:none}.nav .container{gap:16px}.nav-logo{margin-right:auto}.launch-feature a{grid-template-columns:1fr}.launch-feature .action{white-space:normal}.previous-release .container{grid-template-columns:1fr}}</style></head><body><nav class="nav"><div class="container"><a href="/en/" class="nav-logo">Fun<span>ASR</span></a><div class="nav-links"><a href="/en/#capabilities">Capabilities</a><a href="/en/#usage">How to Use</a><a href="/en/#benchmark">Benchmark</a><a href="/en/#demo">Demo</a><a href="https://modelscope.github.io/FunASR/" target="_blank">Docs</a><a href="/en/quickstart.html">Quickstart</a><a href="/en/models.html">Models</a><a href="/en/ecosystem.html">Ecosystem</a><a href="/en/blog/">Blog</a><a href="/en/vs-whisper.html">vs Whisper</a><a href="/en/donors.html">Thanks</a></div><a href="https://www.funasr.com/blog/" style="font-size:0.83rem;font-weight:500;color:var(--text-soft)">中文</a><a href="/go/github" target="_blank" class="nav-btn">GitHub ★</a></div></nav>-<section class="launch-feature"><a href="/en/blog/funasr-v1-4-5-pypi-llama-cpp-release.html"><div><span class="date">August 28, 2026 · Stable release</span><h2>FunASR v1.4.5: Lighter Python Inference and Nine llama.cpp Runtimes</h2><p>No hard torchaudio dependency in the default install, optional kaldi-native-fbank, and one page for PyPI packages, nine runtimes, and SHA-256 checksums.</p></div><span class="action">Read the install and deployment guide →</span></a></section>-<section class="previous-release"><div class="container"><a class="post-card" href="/en/blog/funasr-v1-4-3-pypi-release.html"><span class="date">August 21, 2026 · Stable release</span><h2>FunASR v1.4.3: Optional Silero VAD and Fixed-K Speaker Clustering</h2><p>Millisecond Silero VAD segments, lower-memory clustering for large known-speaker workloads, and 12 SHA-256-addressed release assets.</p></a><a class="post-card" href="/en/blog/funasr-v1-4-0-pypi-release.html"><span class="date">July 31, 2026 · Stable release</span><h2>FunASR v1.4.0: Complete PyPI Packages and Safer AutoModel Arguments</h2><p>SenseVoice and RWKV-BAT package-data fixes, an early vda_model typo guard, and 12 SHA-256-addressed release assets.</p></a><a class="post-card" href="/en/blog/subtitle-edit-fun-asr-sensevoice-local-subtitles.html"><span class="date">August 3, 2026 · Ecosystem</span><h2>Subtitle Edit 5.2: Local Video Subtitles with Fun-ASR Nano or SenseVoice</h2><p>Select a local ASR engine inside a mature subtitle workspace on Windows, macOS, or Linux, with Q4, Q8, and F16 models.</p></a></div></section>+<section class="launch-feature"><a href="/en/blog/funclip-v2-2-0-moss-speaker-clipping.html"><div><span class="date">August 31, 2026 · FunClip v2.2.0</span><h2>MOSS Multi-Speaker Transcription in FunClip: From One Prompt to Speaker Clips</h2><p>Use the vLLM path validated on real two-speaker audio to turn the third-party MOSS model's segment timestamps and speaker labels into SRT and speaker-specific clip exports.</p></div><span class="action">Read the deployment and clipping boundaries →</span></a></section>+<section class="previous-release"><div class="container"><a class="post-card" href="/en/blog/funasr-v1-4-5-pypi-llama-cpp-release.html"><span class="date">August 28, 2026 · Stable release</span><h2>FunASR v1.4.5: Lighter Python Inference and Nine llama.cpp Runtimes</h2><p>No hard torchaudio dependency in the default install, optional kaldi-native-fbank, plus PyPI packages, nine runtimes, and SHA-256 checksums.</p></a><a class="post-card" href="/en/blog/funasr-v1-4-3-pypi-release.html"><span class="date">August 21, 2026 · Stable release</span><h2>FunASR v1.4.3: Optional Silero VAD and Fixed-K Speaker Clustering</h2><p>Millisecond Silero VAD segments, lower-memory clustering for large known-speaker workloads, and 12 SHA-256-addressed release assets.</p></a><a class="post-card" href="/en/blog/funasr-v1-4-0-pypi-release.html"><span class="date">July 31, 2026 · Stable release</span><h2>FunASR v1.4.0: Complete PyPI Packages and Safer AutoModel Arguments</h2><p>SenseVoice and RWKV-BAT package-data fixes, an early vda_model typo guard, and 12 SHA-256-addressed release assets.</p></a><a class="post-card" href="/en/blog/subtitle-edit-fun-asr-sensevoice-local-subtitles.html"><span class="date">August 3, 2026 · Ecosystem</span><h2>Subtitle Edit 5.2: Local Video Subtitles with Fun-ASR Nano or SenseVoice</h2><p>Select a local ASR engine inside a mature subtitle workspace on Windows, macOS, or Linux, with Q4, Q8, and F16 models.</p></a></div></section><article><div class="container"><h1>FunASR Blog</h1><p class="post-meta">Speech recognition deployment, tutorials and best practices</p><a class="post-card" href="/en/blog/speech-to-text-timestamps-python.html"><span class="date">2026-06-23</span><h2>Speech-to-Text with Word/Character-Level Timestamps in Python</h2><p>FunASR Paraformer gives native character timestamps: every char has [start_ms, end_ms] in one call. Build word highlighting, click-to-seek, subtitle alignment. Real output + pairing code.</p></a><a class="post-card" href="/en/blog/punctuation-restoration-python.html"><span class="date">2026-06-23</span><h2>Punctuation Restoration in Python — Add Punctuation to Text / ASR Output</h2><p>FunASR ct-punc: open-source bilingual (zh+en) punctuation restoration. 3 lines of Python to add ,。? (and capitalize English), or attach to ASR in one line. Real output.</p></a><a class="post-card" href="/en/blog/chinese-speech-recognition.html"><span class="date">2026-06-22</span><h2>Chinese (Mandarin) Speech Recognition in Python — Fast & Accurate with FunASR</h2><p>Purpose-built for Chinese: default flagship Fun-ASR-Nano (CER 8.06%), with SenseVoice (7.81%) / Paraformer (10.18%, timestamps/hotwords) for CPU — all far better than Whisper (~20%).</p></a><a class="post-card" href="/en/blog/self-hosted-google-aws-azure-speech-to-text.html"><span class="date">2026-06-22</span><h2>Self-Hosted Speech-to-Text — Free Alternative to Google / AWS / Azure Cloud Speech APIs</h2><p>Open-source (MIT), local inference, no per-minute billing, audio stays on your network, strong Chinese, OpenAI-compatible (migrate via base_url). Runnable code + FunASR vs cloud comparison + cost analysis.</p></a><a class="post-card" href="/en/blog/voice-activity-detection-python.html"><span class="date">2026-06-22</span><h2>Voice Activity Detection in Python — Detect Speech, Remove Silence, Split Audio</h2><p>FunASR fsmn-vad returns millisecond speech spans in 3 lines. Measured: a 13s clip split into 2 segments in 0.12s, 18% silence removed. Trim silence, split long audio, preprocess Whisper to cut hallucinations.</p></a><a class="post-card" href="/en/blog/japanese-speech-recognition.html"><span class="date">2026-06-22</span><h2>Japanese Speech Recognition in Python — SenseVoice: Transcription + Punctuation + Emotion in One Pass</h2><p>Real side-by-side on one Japanese clip: SenseVoice writes 転売 correctly and adds punctuation; Whisper-small gives 天売 with none. Native ja support + auto language ID + emotion/events, 3 lines of Python.</p></a><a class="post-card" href="/en/blog/self-hosted-deepgram-assemblyai-alternative.html"><span class="date">2026-06-23</span><h2>Self-Hosted Deepgram / AssemblyAI Alternative</h2><p>Open-source, free, self-hosted, audio stays local, Chinese-leading, with an OpenAI-compatible API — replace per-minute cloud STT by changing base_url.</p></a><a class="post-card" href="/en/blog/which-funasr-model.html"><span class="date">2026-06-23</span><h2>Which FunASR Model? Nano vs MLT-Nano vs SenseVoice vs Paraformer</h2><p>A decision table with code: flagship Nano for zh/en/ja plus Chinese dialects/accents, separate MLT-Nano for 31 languages, and CPU choices SenseVoice or Paraformer.</p></a><a class="post-card" href="/en/blog/lightweight-speech-recognition-cpu.html"><span class="date">2026-06-22</span><h2>Lightweight Speech Recognition: Chinese ASR in ~250MB on CPU</h2><p>One binary + a 254MB q8 model, no GPU/Python, 0.16s on CPU, 7.99% CER — smaller than whisper.cpp small and ~3x more accurate.</p></a><a class="post-card" href="/en/blog/cantonese-speech-recognition.html"><span class="date">2026-06-21</span><h2>Cantonese Speech Recognition in Python — SenseVoice Keeps Real Cantonese (Whisper Doesn't)</h2><p>Real side-by-side on one Cantonese clip: SenseVoice keeps 呢/唔/嘅, Whisper rewrites to Mandarin. Native yue support + auto language ID, 3 lines of Python.</p></a><a class="post-card" href="/en/blog/funasr-vs-faster-whisper-chinese.html"><span class="date">2026-06-21</span><h2>FunASR vs faster-whisper: Chinese & Cantonese Compared</h2><p>faster-whisper mislabels Cantonese as Mandarin + Japanese homophone errors; SenseVoice handles Cantonese natively, ~2.7x lower CER on Chinese.</p></a><a class="post-card" href="/en/blog/funasr-llama-cpp-whisper-cpp-alternative.html"><span class="date">2026-06-20</span><h2>FunASR on llama.cpp — a whisper.cpp Alternative for Chinese ASR (CPU, no Python)</h2><p>One self-contained binary, built-in VAD, any audio — download and transcribe Chinese; ~2.7x more accurate than whisper.cpp on CPU.</p></a><a class="post-card" href="/en/blog/speech-to-text-python-transcribe-audio.html"><span class="date">2026-06-18</span><h2>Speech to Text in Python with FunASR</h2><p>Transcribe audio in a few lines of Python — timestamps, speakers, batching. Local, free, no API key.</p></a><a class="post-card" href="/en/blog/generate-subtitles-srt-vtt-from-audio-video.html"><span class="date">2026-06-18</span><h2>Auto-Generate Subtitles (SRT & VTT) from Audio or Video with FunASR</h2><p>One command for SRT, Python for VTT too, with speaker labels and real timestamps. Local, free, strong on Chinese.</p></a><a class="post-card" href="/en/blog/self-hosted-openai-whisper-api-alternative.html"><span class="date">2026-06-18</span><h2>Self-Hosted OpenAI Whisper API Alternative with FunASR</h2><p>funasr-server exposes an OpenAI-compatible /v1/audio/transcriptions; the OpenAI SDK works by changing only base_url. Local, free, private.</p></a><a class="post-card" href="/en/blog/funasr-cli-transcribe-command-line.html"><span class="date">2026-06-18</span><h2>Transcribe Audio from the Command Line with FunASR</h2><p>One command -> text/SRT/JSON, --spk for speakers; plus funasr-server for an OpenAI-compatible API.</p></a><a class="post-card" href="/en/blog/funasr-transcribe-long-audio.html"><span class="date">2026-06-17</span><h2>Transcribe Long Audio with FunASR: Hours in One Call</h2><p>Whisper caps at 30s; FunASR ingests any length via built-in VAD - 13 min in 4.3s (186x).</p></a><a class="post-card" href="/en/blog/funasr-realtime-streaming-asr.html"><span class="date">2026-06-17</span><h2>Real-Time Streaming Speech-to-Text with FunASR</h2><p>~600ms low-latency streaming ASR with chunks + cache, plus the 2-pass (streaming + offline) best practice.</p></a><a class="post-card" href="/en/blog/sensevoice-emotion-language-detection.html"><span class="date">2026-06-17</span><h2>Beyond Transcription: Language, Emotion & Audio Events with SenseVoice</h2><p>Transcription + language + emotion + audio events in one pass — the 4-in-1 Whisper cannot do.</p></a><a class="post-card" href="/en/blog/funasr-speaker-diarization.html"><span class="date">2026-06-17</span><h2>Speaker Diarization with FunASR: Who Spoke When</h2><p>Transcription + speaker labels + timestamps in one generate() call. A pyannote+Whisper alternative, no HF gated access.</p></a><a class="post-card" href="/en/blog/funasr-vs-whisper-benchmark.html"><span class="date">2026-06-16</span><h2>FunASR vs Whisper: Real Chinese ASR Benchmark</h2><p>Measured on 184 Chinese files (H100): SenseVoice 169.6x, 7.81% CER — full speed & accuracy data.</p></a><a class="post-card" href="/en/blog/fun-asr-nano-guide.html"><span class="date">2026-06-16</span><h2>Fun-ASR-Nano Guide: 800M End-to-End ASR LLM</h2><p>Flagship for zh/en/ja plus 7 Chinese dialect groups and 26 accents; choose MLT-Nano for 31 languages.</p></a><a class="post-card" href="/en/blog/sensevoice-deployment-guide.html"><span class="date">2026-06-16</span><h2>SenseVoice Deployment Guide: Five-Language ASR, Emotion and Audio Events</h2><p>Multilingual ASR in 3 lines, with language/emotion/event tags, VAD, GPU/CPU.</p></a><p>More: <a href="/en/quickstart.html">Quickstart</a> · <a href="/en/models.html">Models</a></p></div></article><footer><div class="container">© 2024-2026 Tongyi Lab, Alibaba Group · <a href="https://github.com/modelscope/FunASR/blob/main/LICENSE">MIT License</a></div></footer></body></html>diff --git a/web-pages/product-site/legacy/sitemap.xml b/web-pages/product-site/legacy/sitemap.xmlindex ae14af506..d9ea3c623 100644--- a/web-pages/product-site/legacy/sitemap.xml+++ b/web-pages/product-site/legacy/sitemap.xml@@ -12,6 +12,8 @@<url><loc>https://www.funasr.com/en/ecosystem.html</loc><priority>0.8</priority><changefreq>weekly</changefreq></url><url><loc>https://www.funasr.com/blog/</loc><priority>0.9</priority><changefreq>weekly</changefreq></url><url><loc>https://www.funasr.com/en/blog/</loc><priority>0.9</priority><changefreq>weekly</changefreq></url>+ <url><loc>https://www.funasr.com/blog/funclip-v2-2-0-moss-speaker-clipping.html</loc><lastmod>2026-08-31</lastmod><priority>0.9</priority><changefreq>monthly</changefreq></url>+ <url><loc>https://www.funasr.com/en/blog/funclip-v2-2-0-moss-speaker-clipping.html</loc><lastmod>2026-08-31</lastmod><priority>0.9</priority><changefreq>monthly</changefreq></url><url><loc>https://www.funasr.com/blog/funasr-v1-4-5-pypi-llama-cpp-release.html</loc><lastmod>2026-08-28</lastmod><priority>0.9</priority><changefreq>monthly</changefreq></url><url><loc>https://www.funasr.com/en/blog/funasr-v1-4-5-pypi-llama-cpp-release.html</loc><lastmod>2026-08-28</lastmod><priority>0.9</priority><changefreq>monthly</changefreq></url><url><loc>https://www.funasr.com/blog/funasr-v1-4-0-pypi-release.html</loc><lastmod>2026-07-31</lastmod><priority>0.9</priority><changefreq>monthly</changefreq></url>diff --git a/web-pages/product-site/tests/browser/product-site.spec.ts b/web-pages/product-site/tests/browser/product-site.spec.tsindex d2364f7ff..2dae89fda 100644--- a/web-pages/product-site/tests/browser/product-site.spec.ts+++ b/web-pages/product-site/tests/browser/product-site.spec.ts@@ -373,18 +373,20 @@ for (const viewport of [{ name: 'mobile', width: 390, height: 844 },{ name: 'desktop', width: 1440, height: 900 },]) {- test(`v1.4.5 release discovery is stable at ${viewport.name}`, async ({ page }, testInfo) => {+ test(`FunClip v2.2.0 MOSS release discovery is stable at ${viewport.name}`, async ({ page }, testInfo) => {await page.setViewportSize(viewport);for (const release of [{language: 'zh',index: '/blog/',- article: '/blog/funasr-v1-4-5-pypi-llama-cpp-release.html',+ article: '/blog/funclip-v2-2-0-moss-speaker-clipping.html',+ previous: '/blog/funasr-v1-4-5-pypi-llama-cpp-release.html',},{language: 'en',index: '/en/blog/',- article: '/en/blog/funasr-v1-4-5-pypi-llama-cpp-release.html',+ article: '/en/blog/funclip-v2-2-0-moss-speaker-clipping.html',+ previous: '/en/blog/funasr-v1-4-5-pypi-llama-cpp-release.html',},]) {await page.goto(release.index);@@ -392,18 +394,22 @@ for (const viewport of [page.locator(`.launch-feature a[href="${release.article}"]`),).toBeVisible();const history = page.locator('.previous-release .post-card');- await expect(history).toHaveCount(3);+ await expect(history).toHaveCount(4);+ await expect(+ page.locator(`.previous-release a[href="${release.previous}"]`),+ ).toBeVisible();const indexLayout = await history.evaluateAll((cards) => ({overflow: document.documentElement.scrollWidth - document.documentElement.clientWidth,rows: new Set(cards.map((card) => Math.round(card.getBoundingClientRect().top))).size,}));expect(indexLayout.overflow).toBeLessThanOrEqual(1);- expect(indexLayout.rows).toBe(viewport.name === 'mobile' ? 3 : 1);+ expect(indexLayout.rows).toBe(viewport.name === 'mobile' ? 4 : 1);await page.goto(release.article);- await expect(page.locator('h1')).toContainText('FunASR v1.4.5');- await expect(page.getByText('funasr[knf]==1.4.5', { exact: false })).toBeVisible();- await expect(page.getByText('runtime-llamacpp-v0.2.1', { exact: false })).toBeVisible();+ await expect(page.locator('h1')).toContainText('FunClip v2.2.0');+ await expect(page.getByText('OpenMOSS-Team/MOSS-Transcribe-Diarize', { exact: false }).first()).toBeVisible();+ await expect(page.getByText('/v1/audio/transcriptions', { exact: false }).first()).toBeVisible();+ await expect(page.locator('img[src="/img/funclip-v2-1-0-interface.jpg"]')).toBeVisible();const articleLayout = await page.evaluate(() => {const navigation = document.querySelector<HTMLElement>('nav.nav');@@ -419,7 +425,7 @@ for (const viewport of [await page.screenshot({path: testInfo.outputPath(- `v1.4.5-release-${release.language}-${viewport.name}.png`,+ `funclip-v2.2.0-moss-${release.language}-${viewport.name}.png`,),fullPage: true,});diff --git a/web-pages/product-site/tests/test_legacy.py b/web-pages/product-site/tests/test_legacy.pyindex f920e8869..7274fe4ba 100644--- a/web-pages/product-site/tests/test_legacy.py+++ b/web-pages/product-site/tests/test_legacy.py@@ -421,3 +421,53 @@ def test_public_pages_do_not_overstate_sensevoice_language_or_speed_claims():violations.append(path.relative_to(LEGACY).as_posix())assert violations == []+++def test_funclip_v220_moss_release_pages_are_bilingual_indexed_and_verifiable():+ slug = 'funclip-v2-2-0-moss-speaker-clipping.html'+ pages = {+ 'zh': LEGACY / 'blog' / slug,+ 'en': LEGACY / 'en' / 'blog' / slug,+ }+ language_contracts = {+ 'zh': ('第三方模型', '段级时间戳', '不接外部 VAD 或说话人模型'),+ 'en': ('third-party model', 'segment-level timestamps', 'no external VAD or speaker model'),+ }++ for language, path in pages.items():+ text = path.read_text(encoding='utf-8')+ soup = BeautifulSoup(text, 'html.parser')+ hrefs = {link.get('href') for link in soup.select('a[href]')}++ assert 'FunClip v2.2.0' in text+ assert 'OpenMOSS-Team/MOSS-Transcribe-Diarize' in text+ assert 'e8681d68e7042738ffca8ac8212bc8fcb1131ab8' in text+ assert '/v1/audio/transcriptions' in text+ assert 'response_format=json' in text+ assert '994c5d9cf392b74b36284d526eca8bada1560a3e7825ab7baa9c673a1b4ef216' in text+ assert '4f5a7d33d9ea65467f29b55b15ed5be18e64de7e57e2f9f36fe51a23b40557e7' in text+ assert all(marker in text for marker in language_contracts[language])+ assert {+ 'https://github.com/modelscope/FunClip/releases/tag/v2.2.0',+ '/deploy/moss-transcribe-diarize.html'+ if language == 'zh'+ else '/en/deploy/moss-transcribe-diarize.html',+ } <= hrefs++ route = f'/{"" if language == "zh" else "en/"}blog/{slug}'+ peer = f'/{"en/" if language == "zh" else ""}blog/{slug}'+ assert soup.select_one('link[rel="canonical"]')['href'].endswith(route)+ assert soup.select_one(f'link[rel="alternate"][href$="{peer}"]')+ image = soup.select_one('article img[src="/img/funclip-v2-1-0-interface.jpg"]')+ assert image+ metadata = json.loads(soup.select_one('script[type="application/ld+json"]').string)+ assert metadata['datePublished'] == '2026-08-31'+ assert metadata['dateModified'] == '2026-08-31'++ zh_index = (LEGACY / 'blog' / 'index.html').read_text(encoding='utf-8')+ en_index = (LEGACY / 'en' / 'blog' / 'index.html').read_text(encoding='utf-8')+ sitemap = (LEGACY / 'sitemap.xml').read_text(encoding='utf-8')+ assert f'/blog/{slug}' in zh_index+ assert f'/en/blog/{slug}' in en_index+ assert f'https://www.funasr.com/blog/{slug}' in sitemap+ assert f'https://www.funasr.com/en/blog/{slug}' in sitemapdiff --git a/web-pages/product-site/tests/test_output.py b/web-pages/product-site/tests/test_output.pyindex 32a7b0ce8..e470f7797 100644--- a/web-pages/product-site/tests/test_output.py+++ b/web-pages/product-site/tests/test_output.py@@ -609,22 +609,61 @@ def test_v1_4_3_release_blog_is_bilingual_and_verifiable(@pytest.mark.parametrize(- ('relative', 'href'),+ ('relative', 'feature_href', 'history_href'),(- ('blog/index.html', '/blog/funasr-v1-4-5-pypi-llama-cpp-release.html'),- ('en/blog/index.html', '/en/blog/funasr-v1-4-5-pypi-llama-cpp-release.html'),+ (+ 'blog/index.html',+ '/blog/funclip-v2-2-0-moss-speaker-clipping.html',+ '/blog/funasr-v1-4-5-pypi-llama-cpp-release.html',+ ),+ (+ 'en/blog/index.html',+ '/en/blog/funclip-v2-2-0-moss-speaker-clipping.html',+ '/en/blog/funasr-v1-4-5-pypi-llama-cpp-release.html',+ ),),)def test_blog_index_features_latest_release_and_preserves_history(- built_site, relative, href+ built_site, relative, feature_href, history_href):soup = read_soup(built_site / relative)- feature = soup.select_one(f'.launch-feature a[href="{href}"]')+ feature = soup.select_one(f'.launch-feature a[href="{feature_href}"]')assert feature- assert 'v1.4.5' in feature.get_text(' ', strip=True)+ assert 'FunClip v2.2.0' in feature.get_text(' ', strip=True)history = soup.select_one('.previous-release')assert history+ assert history.select_one(f'a[href="{history_href}"]')history_text = history.get_text(' ', strip=True)+ assert 'v1.4.5' in history_textassert 'v1.4.3' in history_textassert 'v1.4.0' in history_text+++ ('relative', 'peer', 'guide'),+ (+ (+ 'blog/funclip-v2-2-0-moss-speaker-clipping.html',+ '/en/blog/funclip-v2-2-0-moss-speaker-clipping.html',+ '/deploy/moss-transcribe-diarize.html',+ ),+ (+ 'en/blog/funclip-v2-2-0-moss-speaker-clipping.html',+ '/blog/funclip-v2-2-0-moss-speaker-clipping.html',+ '/en/deploy/moss-transcribe-diarize.html',+ ),+ ),+)+def test_funclip_v220_blog_builds_with_real_media_and_product_routes(+ built_site, relative, peer, guide+):+ soup = read_soup(built_site / relative)+ assert soup.select_one(f'link[rel="alternate"][href$="{peer}"]')+ image = soup.select_one('article img[src]')+ assert image+ assert (built_site / image['src'].lstrip('/')).is_file()+ assert soup.select_one(f'a[href="{guide}"]')+ assert soup.select_one(+ 'a[href="https://github.com/modelscope/FunClip/releases/tag/v2.2.0"]'+ )