docs: feature Subtitle Edit FunASR integration

web-pages/product-site/content/legacy-manifest.json

@@ -20,7 +20,7 @@
     "blog/funasr-vs-whisper-benchmark.html": "b7b49adf24d20570abb09b733ce03d4a50a4a0e98e746b4a9320f453e01cce84",
     "blog/funclip-v2-1-0-video-clipping-release.html": "88f6c44e5332d1746c4db0fc97d755ef82f12e46d8f1c1c0ad9351152ff9dfc1",
     "blog/generate-subtitles-srt-vtt-from-audio-video.html": "dbaf77072a980c8c50f33cb74e9513dea5dba2d31bd802fade38dcb0bb97e849",
-    "blog/index.html": "ff0057519f7b657ddf737987be2d5eb615286346153fb92fd16d7863ad11eefb",
+    "blog/index.html": "c7b584195fbb15ae797092e4b3305ee811822b6e86223e016f96c5497d0a4e8e",
     "blog/japanese-speech-recognition.html": "90f1f3bee4dcd72e414c6cb1ef9c0e580d5b7107356bc4285ac801affbb64486",
     "blog/lightweight-speech-recognition-cpu.html": "d6270066222ed5baef0df108e6a4155f4a87bb5482169f23f218794d371f3281",
     "blog/punctuation-restoration-python.html": "6cd26e03bf75b4343afd7b351c2681ebd513b058fb549c5888802be9ff3a1229",
@@ -31,14 +31,15 @@
     "blog/sensevoice-emotion-language-detection.html": "6cd2a98e7813921754d33af9b2898f83dc9b1139482a34f2d0bb665189da67ee",
     "blog/speech-to-text-python-transcribe-audio.html": "273c5e6fc6581ae995489d59c9f011de93a6c15e31f08fff56595bc0e6fd866f",
     "blog/speech-to-text-timestamps-python.html": "78364db117dfbce45b03739679764cec7ab1d0a860f321c67154f33392fc6b8d",
+    "blog/subtitle-edit-fun-asr-sensevoice-local-subtitles.html": "f8d5870b6cf9dbdfd4e943fdccb7ae8f091472f1dcbd46bd7db90bd36e3e7846",
     "blog/voice-activity-detection-python.html": "9055206633caecb83c11031f273c8c9297852f44dfe50984e03ab59a7deda6b5",
     "blog/which-funasr-model.html": "0109fe2d66f85c3cc917c822671ec0fb137247ee407f6c33459e6f2cadd05b5d",
     "css/742.48d54c7d.css": "38906de250e9a46352e178d2744831db647ee8dfa8cb6d70cbe68f40e2dfcb5b",
     "css/chunk-vendors.087a2961.css": "aa90b6322d18cf3f5f6199516471604c803caeffb1893167671eb9026de65db4",
     "css/index.1682178c.css": "b5f6034ce886c25773928c114e4290d1c491a3d081677b488810198efd76b4e1",
     "decoder.js": "f2023a28036b1ff58e5bdabbb72ea427f8faaf60e89acd78ff183c313bdb0a2c",
     "donors.html": "eec6b789b29c27d372925ae0ad3e13d4c6e62978b3c38c4da9e3aec129f10934",
-    "ecosystem.html": "6c547fd83f245652513fcd739db7d314cf8b3b6b9e4ce75b1840cff58039dab0",
+    "ecosystem.html": "1defb2b8de27bbb85290813f8f9263b96fe5b9c67c821165645fca26d52d19b6",
     "en/blog/cantonese-speech-recognition.html": "b9bd146198206f781c37f341c370a690dc83cd7163334e34b4e7f65e69af8ff2",
     "en/blog/chinese-speech-recognition.html": "16b68bd2a1122236c580c62275002ae2c0875ca14e32686e88d3b5ccfa9f56ef",
     "en/blog/fun-asr-nano-guide.html": "1746c708bd0606188de4266d8255984dd9e14634af33c54ad65a5f05b767be1b",
@@ -55,7 +56,7 @@
     "en/blog/funasr-vs-whisper-benchmark.html": "367d4a8a1cc09ac932c80cdad065127925c5e5f942a806ace683c16dc1132769",
     "en/blog/funclip-v2-1-0-video-clipping-release.html": "229baf59adf2c3290541d9b3c8a6243992406ba84b712714e9d14599205cb1d4",
     "en/blog/generate-subtitles-srt-vtt-from-audio-video.html": "bd81aa43c6a977f28dd3925861bf456002fbacfec0df0504b413daa64ae60dfa",
-    "en/blog/index.html": "19080d45223511743fda663d076835dff88c9011d9840ee85d1a21dc754d5787",
+    "en/blog/index.html": "ac522ccc02a3df9688fa3ea21f13480f2ca4c996b7dcd4f66fbb28806775ccbe",
     "en/blog/japanese-speech-recognition.html": "8b106563142c291d3b86fad79a51e9c8746417b7750430e91296cc90764e570f",
     "en/blog/lightweight-speech-recognition-cpu.html": "0e02c0e0853b12613d32c250f593c05c2052f18231207b63ee01d6e6600a86f7",
     "en/blog/punctuation-restoration-python.html": "d6e30049f48d9dc6e6bc22eb567830013e4161eca51215616738b675dd1ffc40",
@@ -66,10 +67,11 @@
     "en/blog/sensevoice-emotion-language-detection.html": "35ea4c9fc89b95b7b0de75c6138058717271d22222d5d0c502add275c068c794",
     "en/blog/speech-to-text-python-transcribe-audio.html": "225d4334c591d53aa126d4f31bc4eb0cbaf0afb63c2486c7c934757a0a3627b9",
     "en/blog/speech-to-text-timestamps-python.html": "6a7f8368f757c9ea50e287db6db3191ebcbbfc914f9a869b9515648b2d69790b",
+    "en/blog/subtitle-edit-fun-asr-sensevoice-local-subtitles.html": "7c65a73bab1ff481d9b398476ea6440926546ba7122cc2cb64f5bda81fc039a2",
     "en/blog/voice-activity-detection-python.html": "d12f5d0f4ae07c3434f6188d12f5603b8abb9578413b79133668638d1c5e18a7",
     "en/blog/which-funasr-model.html": "1207180aa929a3aa51db136c1098f4edc8f07405e2b56fe033998bf996f8ec7f",
     "en/donors.html": "eacb7f9434b1b29e13e9b0175bb9680556ee72ab4dbd155e68f9c912eb0212b1",
-    "en/ecosystem.html": "e498a8740c1cdf757556b40941b77f470ad51fb744d29e98025b4293e7e96f2e",
+    "en/ecosystem.html": "3b7dc72e8925d60716e144ea8771ca433275cf1281ba29cb872d15fc7451e3f2",
     "en/index.html": "4950bc2e0b337637300c5bcd45d1820d9636c4f1dab34e0ec8d3443be44bd277",
     "en/llama-cpp.html": "dbfbd125ebbf07f7d923c91b122818f8b09484ce54c1e80eba66a89d22dfb5b4",
     "en/models.html": "c2add621edc3aa63e6d49587f089ee5ac6c05faf5f68e14fef70a7a5ab443a4d",
@@ -84,6 +86,7 @@
     "img/mxjs-bg.e085eb31.png": "773f9462b525ad6b74e96387217e543d238a12b2af7f6c0d089f745291079551",
     "img/mxjs.6724be62.png": "9d398c1aa1e55de7b3d7729886d5f2866c31f00e82c3b36ea7740d02e60ee1aa",
     "img/sstx-bg.d7e580c1.png": "33a6bd3159f3748244f3c27545314010a33bb7d9749c95be3fc24f0075741a62",
+    "img/subtitle-edit-speech-to-text.png": "3ea166b3dc21ab262418d40616852360e1c10aaba22a2365bfd4b1c238972e15",
     "index.html": "95aa61940d7e48d3210899ec4b7d22bbd198ef7e3721b117e1e489f1e7b47b1a",
     "index.js": "f10e5fff91ed36af5377609eefa067c7e22278d0dd8e558f065733ca99b93fd6",
     "jessibuca.js": "02240fc0fdfa74ebe840cc6c818fc91a9c3cb830d9ebeddd9ca21b46168aa06f",

web-pages/product-site/legacy/blog/index.html

@@ -42,13 +42,13 @@
 .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 .post-card{margin-bottom:0}
+.previous-release{padding-top:16px}.previous-release .container{display:grid;grid-template-columns:1fr 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}}
+@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="https://github.com/modelscope/FunASR" target="_blank" class="nav-btn">GitHub ★</a></div></nav>
 <section class="launch-feature"><a href="/blog/funasr-v1-4-0-pypi-release.html"><div><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></div><span class="action">查看发布与校验指南 →</span></a></section>
-<section class="previous-release"><div class="container"><a class="post-card" href="/blog/funclip-v2-1-0-video-clipping-release.html"><span class="date">2026-07-24</span><h2>FunClip v2.1.0：本地 AI 视频剪辑的首个版本化发布</h2><p>Paraformer、Fun-ASR-Nano、SenseVoice 与大模型剪辑，提供可校验、可回退的源码下载。</p></a></div></section>
+<section class="previous-release"><div class="container"><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><a class="post-card" href="/blog/funclip-v2-1-0-video-clipping-release.html"><span class="date">2026-07-24</span><h2>FunClip v2.1.0：本地 AI 视频剪辑的首个版本化发布</h2><p>Paraformer、Fun-ASR-Nano、SenseVoice 与大模型剪辑，提供可校验、可回退的源码下载。</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:比 Whisper 快 15 倍</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>