mirror of
https://github.com/modelscope/FunASR.git
synced 2026-10-12 02:19:18 +00:00
zhifu gaoandLauraGPT
84e049ed48
* docs: design product deployment hub * docs(site): plan deployment product hub implementation * feat(site): add deployment evidence registry * feat(site): add deployment recommendation engine * build(site): track reproducible live-site corpus * feat(site): build bilingual deployment product surface * feat(site): add deployment contracts and benchmarks * feat(site): preserve legacy routes and unify navigation * ci(site): validate reproducible product builds * ops(site): add atomic releases and hardened nginx * test(site): add responsive product browser coverage * fix(site): support managed and manual nginx masters * fix(site): make release smoke routes configurable * docs(site): record product hub rollout --------- Co-authored-by: LauraGPT <[email protected]>
136 lines
13 KiB
HTML
136 lines
13 KiB
HTML
<!DOCTYPE html>
|
||
<html lang="zh">
|
||
<head>
|
||
<meta charset="utf-8">
|
||
<meta name="viewport" content="width=device-width,initial-scale=1">
|
||
<title>标点恢复(Punctuation Restoration)Python 实战:给无标点文本/ASR 结果自动加标点 | FunASR 博客</title>
|
||
<meta name="description" content="怎么给无标点的文本或语音识别结果自动加标点?FunASR ct-punc 是开源标点恢复模型,中英文双语,3 行 Python 补全 ，。？,英文还做句首大写;也能一行挂到 ASR 上。附真实实测输出。">
|
||
<meta name="keywords" content="标点恢复, 文本加标点, 标点预测, 标点符号恢复, punctuation restoration, add punctuation to text python, ct-punc, ASR 后处理, FunASR, 语音识别标点">
|
||
<link rel="icon" href="/logo.png">
|
||
<meta property="og:title" content="标点恢复(Punctuation Restoration)Python 实战:给无标点文本/ASR 结果自动加标点 | FunASR 博客">
|
||
<meta property="og:description" content="怎么给无标点的文本或语音识别结果自动加标点?FunASR ct-punc 是开源标点恢复模型,中英文双语,3 行 Python 补全 ，。？,英文还做句首大写;也能一行挂到 ASR 上。附真实实测输出。">
|
||
<meta property="og:type" content="article">
|
||
<meta property="og:url" content="https://www.funasr.com/blog/punctuation-restoration-python.html">
|
||
<meta property="og:image" content="https://www.funasr.com/logo.png">
|
||
<link rel="canonical" href="https://www.funasr.com/blog/punctuation-restoration-python.html">
|
||
<link rel="alternate" hreflang="en" href="https://www.funasr.com/en/blog/punctuation-restoration-python.html">
|
||
<link rel="alternate" hreflang="zh" href="https://www.funasr.com/blog/punctuation-restoration-python.html">
|
||
<link rel="alternate" hreflang="x-default" href="https://www.funasr.com/en/blog/punctuation-restoration-python.html">
|
||
<link href="https://fonts.googleapis.com/css2?family=Inter:wght@400;500;600;700;800&display=swap" rel="stylesheet">
|
||
<script type="application/ld+json">
|
||
{"@context":"https://schema.org","@type":"BlogPosting","headline":"标点恢复(Punctuation Restoration)Python 实战:给无标点文本/ASR 结果自动加标点 | FunASR 博客","description":"怎么给无标点的文本或语音识别结果自动加标点?FunASR ct-punc 是开源标点恢复模型,中英文双语,3 行 Python 补全 ，。？,英文还做句首大写;也能一行挂到 ASR 上。附真实实测输出。","datePublished":"2026-06-23","dateModified":"2026-06-23","author":{"@type":"Organization","name":"FunASR / Tongyi Lab"},"publisher":{"@type":"Organization","name":"FunASR","logo":{"@type":"ImageObject","url":"https://www.funasr.com/logo.png"}},"mainEntityOfPage":{"@type":"WebPage","@id":"https://www.funasr.com/blog/punctuation-restoration-python.html"},"image":"https://www.funasr.com/logo.png"}
|
||
</script>
|
||
<style>:root{--primary:#2563eb;--primary-dark:#1d4ed8;--bg:#fff;--surface:#f8fafc;--border:#e2e8f0;--text:#0f172a;--text-soft:#475569;--text-muted:#94a3b8;--radius:12px}
|
||
*{margin:0;padding:0;box-sizing:border-box}
|
||
body{font-family:'Inter',-apple-system,sans-serif;color:var(--text);line-height:1.7}
|
||
a{color:var(--primary);text-decoration:none}a:hover{text-decoration:underline}
|
||
.container{max-width:800px;margin:0 auto;padding:0 24px}
|
||
.nav{position:fixed;top:0;left:0;right:0;z-index:100;background:rgba(255,255,255,0.9);backdrop-filter:blur(12px);border-bottom:1px solid var(--border);padding:14px 0}
|
||
.nav .container{max-width:1120px;display:flex;align-items:center;gap:24px}
|
||
.nav-logo{font-size:1.2rem;font-weight:800;color:var(--text)}.nav-logo span{color:var(--primary)}
|
||
.nav-links{display:flex;gap:20px;margin-left:auto;flex-wrap:wrap}
|
||
.nav-links a{font-size:0.85rem;font-weight:500;color:var(--text-soft)}
|
||
.nav-btn{padding:7px 16px;background:var(--primary);color:#fff;border-radius:7px;font-size:0.83rem;font-weight:600}
|
||
article{padding:120px 0 80px}
|
||
h1{font-size:2rem;font-weight:800;line-height:1.3;margin-bottom:14px}
|
||
h2{font-size:1.3rem;font-weight:700;margin:36px 0 14px;padding-top:16px;border-top:1px solid var(--border)}
|
||
h3{font-size:1.05rem;font-weight:700;margin:22px 0 10px}
|
||
p{margin-bottom:14px;color:var(--text-soft)}
|
||
ul,ol{margin:0 0 14px 22px;color:var(--text-soft)}li{margin-bottom:6px}
|
||
table{width:100%;border-collapse:collapse;margin:16px 0;font-size:0.86rem}
|
||
th,td{padding:10px 12px;text-align:left;border-bottom:1px solid var(--border)}
|
||
th{font-weight:600;background:var(--surface);font-size:0.78rem;color:var(--text-muted)}
|
||
pre{background:#1e293b;color:#e2e8f0;padding:18px;border-radius:10px;overflow-x:auto;font-size:0.82rem;line-height:1.7;margin:14px 0}
|
||
code{font-family:ui-monospace,Menlo,monospace}
|
||
p code,li code{background:var(--surface);padding:2px 6px;border-radius:5px;font-size:0.85em;color:var(--primary-dark)}
|
||
.post-meta{color:var(--text-muted);font-size:0.85rem;margin-bottom:24px}
|
||
.cta{background:var(--surface);border:1px solid var(--border);border-radius:var(--radius);padding:24px;margin:28px 0;text-align:center}
|
||
.cta a.btn{display:inline-block;padding:10px 24px;background:var(--primary);color:#fff;border-radius:8px;font-weight:600}
|
||
.post-list{list-style:none;margin:0;padding:0}
|
||
.post-list li{margin:0 0 8px}
|
||
.post-card{display:block;border:1px solid var(--border);border-radius:var(--radius);padding:20px 22px;margin-bottom:14px}
|
||
.post-card:hover{border-color:var(--primary);text-decoration:none}
|
||
.post-card h2{border:none;padding:0;margin:0 0 6px;font-size:1.15rem;color:var(--text)}
|
||
.post-card p{margin:0;color:var(--text-soft);font-size:0.9rem}
|
||
.post-card .date{color:var(--text-muted);font-size:0.8rem}
|
||
footer{background:#0f172a;color:#94a3b8;padding:28px 0;text-align:center;font-size:0.8rem}
|
||
footer a{color:#94a3b8}</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/punctuation-restoration-python.html" 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>
|
||
<article><div class="container">
|
||
<h1>标点恢复(Punctuation Restoration)Python 实战:给无标点文本/ASR 结果自动加标点</h1>
|
||
<p class="post-meta">2026-06-23 · FunASR 团队</p>
|
||
|
||
<p>很多语音识别(ASR)模型输出的是<strong>没有标点</strong>的纯文本——一长串字读起来很费劲。<strong>标点恢复</strong>就是把"。""，""？"这些标点自动补回去,让转写结果可读。<strong>FunASR 的 <code>ct-punc</code></strong> 是一个开源的标点恢复模型,<strong>中英文都支持</strong>,3 行 Python 就能给任意文本加标点。下面全是真实实测输出。</p>
|
||
|
||
<h2>3 行代码做标点恢复(实测输出)</h2>
|
||
<pre>pip install funasr
|
||
|
||
from funasr import AutoModel
|
||
|
||
model = AutoModel(model="ct-punc", disable_update=True)
|
||
print(model.generate(input="我们都是木头人不许说话不许动")[0]["text"])
|
||
# 我们都是木头人，不许说话，不许动。</pre>
|
||
<p>输入是没有标点的连续文本,输出自动补上了逗号和句号。</p>
|
||
|
||
<h2>中英文真实示例</h2>
|
||
<table>
|
||
<tr><th>输入(无标点)</th><th>输出(ct-punc 加标点)</th></tr>
|
||
<tr><td>我们都是木头人不许说话不许动</td><td>我们都是木头人，不许说话，不许动。</td></tr>
|
||
<tr><td>今天天气怎么样我想出去走走你要一起吗</td><td>今天天气怎么样，我想出去走走，你要一起<strong>吗？</strong></td></tr>
|
||
<tr><td>the meeting is at 3 pm please bring your laptop and the report</td><td><strong>T</strong>he meeting is at 3 pm<strong>,</strong> please bring your laptop and the report<strong>.</strong></td></tr>
|
||
</table>
|
||
<p>可以看到:中文补「，。？」(问句还会自动判断用<strong>问号</strong>);英文补逗号、句号,还会把<strong>句首字母大写</strong>。同一个模型双语通吃。</p>
|
||
|
||
<h2>最常见用法:给 ASR 结果加标点</h2>
|
||
<p>标点恢复最大的用处是清洗语音识别的输出。FunASR 的 ASR 模型可以<strong>一行挂载</strong> ct-punc,识别完直接带标点:</p>
|
||
<pre>from funasr import AutoModel
|
||
|
||
# ASR + VAD + 标点,一次完成(以中文 Paraformer 为例)
|
||
model = AutoModel(model="paraformer-zh", vad_model="fsmn-vad", punc_model="ct-punc")
|
||
result = model.generate(input="audio.wav")
|
||
print(result[0]["text"]) # 输出已带标点</pre>
|
||
<p>当然你也可以像最上面那样<strong>单独</strong>用 ct-punc 处理任意文本——不限于语音,任何无标点文本(老字幕、OCR 结果、聊天记录)都能加标点。</p>
|
||
|
||
<h2>为什么用 ct-punc</h2>
|
||
<table>
|
||
<tr><th></th><th>ct-punc(FunASR)</th></tr>
|
||
<tr><td>语言</td><td>中文 + 英文(单模型双语)</td></tr>
|
||
<tr><td>用法</td><td>3 行 Python,输入文本即可;也能一行挂到 ASR 上</td></tr>
|
||
<tr><td>标点</td><td>，。？等;英文还做句首大写</td></tr>
|
||
<tr><td>许可证</td><td>开源,可商用</td></tr>
|
||
</table>
|
||
<p>想要完整的语音流程,看 <a href="/blog/chinese-speech-recognition.html">中文语音识别实战</a>、<a href="/blog/voice-activity-detection-python.html">VAD/去静音</a> 和 <a href="/blog/funasr-speaker-diarization.html">说话人分离</a>;不确定选哪个 ASR 模型看 <a href="/blog/which-funasr-model.html">模型选型指南</a>(默认推荐旗舰 Fun-ASR-Nano)。</p>
|
||
|
||
<div class="cta"><p><strong>FunASR 全家桶开源(MIT)</strong>——标点恢复、ASR、VAD、说话人、情感、LLM-ASR(旗舰 Fun-ASR-Nano),拿来即用。觉得有用就点个 Star 👇</p><p><a class="btn" href="https://github.com/modelscope/FunASR" target="_blank">⭐ Star FunASR</a></p><p style="margin-top:10px;font-size:0.85rem">也欢迎 Star:<a href="https://github.com/QwenAudio/SenseVoice" target="_blank">SenseVoice</a> · <a href="https://github.com/QwenAudio/Fun-ASR" target="_blank">Fun-ASR</a> · <a href="https://github.com/modelscope/FunClip" target="_blank">FunClip</a></p></div>
|
||
<!--related-posts-->
|
||
<h2>相关文章</h2>
|
||
<ul class="post-list">
|
||
<li><a href="/blog/funasr-vs-whisper-benchmark.html">FunASR vs Whisper 实测对比</a></li>
|
||
<li><a href="/blog/sensevoice-deployment-guide.html">SenseVoice 部署指南</a></li>
|
||
<li><a href="/blog/fun-asr-nano-guide.html">Fun-ASR-Nano 使用指南</a></li>
|
||
<li><a href="/blog/funasr-speaker-diarization.html">说话人分离:谁在何时说话</a></li>
|
||
<li><a href="/blog/sensevoice-emotion-language-detection.html">情感与语种检测</a></li>
|
||
<li><a href="/blog/funasr-realtime-streaming-asr.html">实时流式语音识别</a></li>
|
||
<li><a href="/blog/funasr-transcribe-long-audio.html">转写超长音频(1小时一次搞定)</a></li>
|
||
<li><a href="/blog/funasr-cli-transcribe-command-line.html">命令行转写(文本/JSON/SRT)</a></li>
|
||
<li><a href="/blog/self-hosted-openai-whisper-api-alternative.html">自托管 OpenAI Whisper API 替代</a></li>
|
||
<li><a href="/blog/generate-subtitles-srt-vtt-from-audio-video.html">自动生成字幕(SRT / VTT)</a></li>
|
||
<li><a href="/blog/speech-to-text-python-transcribe-audio.html">Python 语音转文字教程</a></li>
|
||
<li><a href="/blog/funasr-llama-cpp-whisper-cpp-alternative.html">FunASR 跑进 llama.cpp(whisper.cpp 替代)</a></li>
|
||
<li><a href="/blog/funasr-vs-faster-whisper-chinese.html">FunASR vs faster-whisper(中文/粤语)</a></li>
|
||
<li><a href="/blog/lightweight-speech-recognition-cpu.html">轻量语音识别(CPU 250MB)</a></li>
|
||
<li><a href="/blog/self-hosted-deepgram-assemblyai-alternative.html">自托管替代 Deepgram/AssemblyAI</a></li>
|
||
<li><a href="/blog/which-funasr-model.html">选哪个 FunASR 模型</a></li>
|
||
<li><a href="/blog/cantonese-speech-recognition.html">粤语语音识别(SenseVoice 原生粤语)</a></li>
|
||
<li><a href="/blog/japanese-speech-recognition.html">日语语音识别(SenseVoice 转写+标点+情感)</a></li>
|
||
<li><a href="/blog/voice-activity-detection-python.html">Python 语音活动检测(VAD)</a></li>
|
||
<li><a href="/blog/self-hosted-google-aws-azure-speech-to-text.html">自托管替代 Google/AWS/Azure 云语音 API</a></li>
|
||
<li><a href="/blog/chinese-speech-recognition.html">中文语音识别(普通话)实战</a></li>
|
||
<li><a href="/blog/speech-to-text-timestamps-python.html">语音识别带时间戳(字级)</a></li>
|
||
</ul>
|
||
</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> |