mirror of
https://github.com/modelscope/FunASR.git
synced 2026-10-12 02:19:18 +00:00
382 lines
22 KiB
HTML
382 lines
22 KiB
HTML
<!DOCTYPE html>
|
||
|
||
<html lang="zh-CN">
|
||
<head>
|
||
<meta charset="utf-8"/>
|
||
<meta content="width=device-width, initial-scale=1" name="viewport"/>
|
||
<title>选择第一个模型 - FunASR</title>
|
||
<meta content="选择第一个模型" name="description"/>
|
||
<meta content="#ffffff" name="theme-color"/>
|
||
<link href="https://www.funasr.com/docs/model-selection.html" rel="canonical"/>
|
||
<link href="https://www.funasr.com/en/docs/model-selection.html" hreflang="en" rel="alternate"/>
|
||
<link href="https://www.funasr.com/docs/model-selection.html" hreflang="zh-CN" rel="alternate"/>
|
||
<meta content="website" property="og:type"/>
|
||
<meta content="选择第一个模型 - FunASR" property="og:title"/>
|
||
<meta content="选择第一个模型" property="og:description"/>
|
||
<meta content="https://www.funasr.com/docs/model-selection.html" property="og:url"/>
|
||
<link href="../assets/css/site.7be954c8e106.css" rel="stylesheet"/>
|
||
<link href="../assets/css/experience.34d6e632686e.css" rel="stylesheet"/>
|
||
<script type="application/ld+json">{"@context": "https://schema.org", "@type": "SoftwareApplication", "applicationCategory": "DeveloperApplication", "codeRepository": "https://github.com/modelscope/FunASR", "dateModified": "2026-09-01", "license": "https://github.com/modelscope/FunASR/blob/main/LICENSE", "name": "FunASR", "operatingSystem": "Linux, macOS, Windows", "url": "https://www.funasr.com/docs/model-selection.html"}</script></head>
|
||
<body data-copy-icon="../assets/lucide/copy.ea80e566c7a1.svg" data-language="zh" data-route="/docs/model-selection.html">
|
||
<a class="skip-link" href="#main">跳到主要内容</a>
|
||
<header class="site-header">
|
||
<a aria-label="FunASR 首页" class="brand" href="https://www.funasr.com/">
|
||
<span aria-hidden="true" class="brand-mark">F</span>
|
||
<span>FunASR</span>
|
||
</a>
|
||
<button aria-controls="primary-navigation" aria-expanded="false" class="icon-button menu-button" data-menu-toggle="" title="打开目录" type="button">
|
||
<img alt="" src="../assets/lucide/menu.90a31b3ab1cf.svg"/>
|
||
</button>
|
||
<nav aria-label="主目录" class="primary-navigation" data-primary-nav="" id="primary-navigation">
|
||
<a href="https://www.funasr.com/">产品</a>
|
||
<a href="https://www.funasr.com/deploy/">部署</a>
|
||
<a href="https://www.funasr.com/models.html">模型</a>
|
||
<a href="https://www.funasr.com/benchmarks.html">性能</a>
|
||
<a href="https://www.funasr.com/ecosystem.html">生态</a>
|
||
<a href="https://www.funasr.com/blog/">博客</a>
|
||
<a href="https://www.funasr.com/docs/">文档</a>
|
||
<a href="https://www.funasr.com/donors.html">功德榜</a>
|
||
</nav>
|
||
<div class="header-actions">
|
||
<a class="icon-link" href="https://www.funasr.com/en/docs/model-selection.html" title="English">
|
||
<img alt="" src="../assets/lucide/languages.ae9048feb2c7.svg"/>
|
||
<span>EN</span>
|
||
</a>
|
||
<a aria-label="GitHub" class="icon-button" href="https://www.funasr.com/go/github" title="GitHub">
|
||
<img alt="" src="../assets/lucide/github.793554449a30.svg"/>
|
||
</a>
|
||
</div>
|
||
</header>
|
||
<main id="main">
|
||
<div class="docs-layout">
|
||
<aside class="docs-sidebar">
|
||
<a class="docs-home" href="https://www.funasr.com/docs/">文档中心</a>
|
||
<details class="docs-navigation" open="">
|
||
<summary class="docs-navigation-toggle">浏览目录</summary>
|
||
<details open="">
|
||
<summary>开始使用</summary>
|
||
<nav aria-label="开始使用">
|
||
<a href="https://www.funasr.com/docs/native-transformers.html">Transformers 快速开始</a>
|
||
<a href="https://www.funasr.com/docs/installation.html">安装与环境验证</a>
|
||
<a href="https://www.funasr.com/docs/quickstart.html">第一次转写</a>
|
||
<a href="https://www.funasr.com/docs/python-api.html">Python SDK: AutoModel</a>
|
||
<a aria-current="page" href="https://www.funasr.com/docs/model-selection.html">选择第一个模型</a>
|
||
<a href="https://www.funasr.com/docs/command-line.html">命令行转写</a>
|
||
<a href="https://www.funasr.com/docs/migration.html">从 Whisper 与云 API 迁移</a>
|
||
</nav>
|
||
</details>
|
||
<details open="">
|
||
<summary>模型与能力</summary>
|
||
<nav aria-label="模型与能力">
|
||
<a href="https://www.funasr.com/docs/moss-transcribe-diarize.html">MOSS 转写与说话人分离</a>
|
||
<a href="https://www.funasr.com/docs/model-zoo.html">Model Zoo</a>
|
||
<a href="https://www.funasr.com/docs/streaming-vad.html">流式语音活动检测</a>
|
||
<a href="https://www.funasr.com/docs/keyword-spotting.html">关键词检测</a>
|
||
<a href="https://www.funasr.com/docs/speaker-emotion.html">说话人与情感标签</a>
|
||
</nav>
|
||
</details>
|
||
<details open="">
|
||
<summary>训练与扩展</summary>
|
||
<nav aria-label="训练与扩展">
|
||
<a href="https://www.funasr.com/docs/training.html">微调与评测</a>
|
||
<a href="https://www.funasr.com/docs/model-registration.html">自定义模型注册</a>
|
||
</nav>
|
||
</details>
|
||
<details open="">
|
||
<summary>部署与接口</summary>
|
||
<nav aria-label="部署与接口">
|
||
<a href="https://www.funasr.com/docs/docker.html">容器环境与镜像选择</a>
|
||
<a href="https://www.funasr.com/docs/runtime-guide.html">服务部署入口</a>
|
||
<a href="https://www.funasr.com/docs/http-server.html">Python HTTP 服务</a>
|
||
<a href="https://www.funasr.com/docs/kubernetes.html">Kubernetes 部署</a>
|
||
<a href="https://www.funasr.com/docs/deployment-matrix.html">运行时与部署矩阵</a>
|
||
<a href="https://www.funasr.com/docs/vllm.html">vLLM split-engine 推理</a>
|
||
<a href="https://www.funasr.com/docs/official-native-vllm.html">官方原生 vLLM 功能验证(2026-09-07)</a>
|
||
<a href="https://www.funasr.com/docs/native-vllm.html">社区原生 vLLM 历史记录(2026-08-13)</a>
|
||
</nav>
|
||
</details>
|
||
<details open="">
|
||
<summary>评测与运维</summary>
|
||
<nav aria-label="评测与运维">
|
||
<a href="https://www.funasr.com/docs/troubleshooting.html">安装与推理故障排查</a>
|
||
<a href="https://www.funasr.com/docs/security.html">服务安全边界</a>
|
||
<a href="https://www.funasr.com/docs/benchmark-method.html">可复现性能评测</a>
|
||
<a href="https://www.funasr.com/docs/historical-asr-benchmark.html">历史 ASR 评测</a>
|
||
<a href="https://www.funasr.com/docs/realtime-benchmark.html">实时 WebSocket 压测</a>
|
||
</nav>
|
||
</details>
|
||
<details open="">
|
||
<summary>应用与生态</summary>
|
||
<nav aria-label="应用与生态">
|
||
<a href="https://www.funasr.com/docs/agent-integration.html">Agent 集成</a>
|
||
<a href="https://www.funasr.com/docs/use-cases.html">应用场景与示例</a>
|
||
<a href="https://www.funasr.com/docs/community.html">社区集成</a>
|
||
<a href="https://www.funasr.com/docs/repositories.html">四仓职责与贡献入口</a>
|
||
<a href="https://www.funasr.com/docs/javascript.html">JavaScript 客户端</a>
|
||
<a href="https://www.funasr.com/docs/gradio.html">Gradio 浏览器客户端</a>
|
||
<a href="https://www.funasr.com/docs/workflows.html">工作流集成</a>
|
||
</nav>
|
||
</details>
|
||
<details open="">
|
||
<summary>协议与参考</summary>
|
||
<nav aria-label="协议与参考">
|
||
<a href="https://www.funasr.com/docs/service-api.html">HTTP API 契约</a>
|
||
<a href="https://www.funasr.com/docs/websocket-protocol.html">C++ WebSocket 协议</a>
|
||
<a href="https://www.funasr.com/docs/onnx-output.html">ONNX 二进制输出契约</a>
|
||
</nav>
|
||
</details>
|
||
<a href="https://www.funasr.com/deploy/">部署手册 →</a>
|
||
</details>
|
||
</aside>
|
||
<div class="docs-body">
|
||
<nav aria-label="面包屑" class="breadcrumbs"><a href="https://www.funasr.com/">FunASR</a><span>/</span><a href="https://www.funasr.com/docs/">文档</a><span>/</span><span>选择第一个模型</span></nav>
|
||
<header class="docs-title"><h1>选择第一个模型</h1><a class="source-link" data-source-link="" href="https://github.com/modelscope/FunASR/blob/main/docs/model_selection_zh.md">查看 / 编辑源文档 ↗</a></header>
|
||
<article class="docs-article"><div class="source-title-anchor" id="funasr-模型选择指南"></div>
|
||
<h2 id="先用-transformers-体验-nano">先用 Transformers 体验 Nano</h2>
|
||
<p>通过 Hugging Face API 转写中、英、日语音,先用 <a href="https://www.funasr.com/docs/native-transformers.html">原生 Transformers 5.17.0</a>、官方 <code>FunAudioLLM/Fun-ASR-Nano-2512-hf</code> 权重和 CPU 示例。下文的工具库与服务路径仍独立;原生导出不自动提供时间戳、说话人或 HTTP 接口。</p>
|
||
<p>当你第一次选择模型、评估是否从 Whisper 或云端 ASR 迁移,或者准备通过 OpenAI 兼容 API 暴露模型别名时,可以先看这份指南。</p>
|
||
<span data-legacy-doc-anchor="默认快速路径" id="default"></span><h2 id="默认快速路径">默认快速路径</h2>
|
||
<p>如果有 GPU,需要评估中文、英文、日语或中文方言和地域口音,可以先试旗舰 <strong>Fun-ASR-Nano</strong>(SenseVoice 编码器 + Qwen3 解码器)。确定生产模型前,请用自己的音频做对比:</p>
|
||
<pre id="code-0"><code class="language-python">from funasr import AutoModel
|
||
|
||
model = AutoModel(model="FunAudioLLM/Fun-ASR-Nano-2512", device="cuda")
|
||
result = model.generate(input="meeting.wav")
|
||
print(result[0]["text"])
|
||
</code></pre>
|
||
<p>需要非自回归多语种 ASR、情感/事件标签,或先在 CPU 上评估时,可以从 <strong>SenseVoice-Small</strong> 开始。下面的会议转写示例另外组合了 VAD 和说话人处理阶段;说话人分离不是 SenseVoice 单次识别直接提供的能力:</p>
|
||
<pre id="code-1"><code class="language-python">from funasr import AutoModel
|
||
|
||
model = AutoModel(
|
||
model="iic/SenseVoiceSmall",
|
||
vad_model="fsmn-vad",
|
||
spk_model="cam++",
|
||
device="cuda", # 便携 smoke test 可改为 "cpu"
|
||
)
|
||
result = model.generate(input="meeting.wav")
|
||
</code></pre>
|
||
<p>SenseVoice 生成转写和富文本标签;<code>fsmn-vad</code> 定位语音,<code>cam++</code> 提取说话人向量,
|
||
再由处理流水线聚类得到录音内的匿名编号。这些编号不识别已注册人物,也不是跨录音稳定的身份。</p>
|
||
<p>当你的场景是纯中文、需要字级时间戳或热词时,切换到 Paraformer。</p>
|
||
<span data-legacy-doc-anchor="决策表" id="decision"></span><h2 id="决策表">决策表</h2>
|
||
<table>
|
||
<thead>
|
||
<tr>
|
||
<th>需求</th>
|
||
<th>优先尝试</th>
|
||
<th>原因</th>
|
||
<th>下一步文档</th>
|
||
</tr>
|
||
</thead>
|
||
<tbody>
|
||
<tr>
|
||
<td>快速多语种私有转写</td>
|
||
<td>SenseVoice-Small</td>
|
||
<td>兼顾 ASR、情感标签、音频事件标签和 CPU 可用性。</td>
|
||
<td><a href="https://github.com/modelscope/FunASR/blob/main/README_zh.md#快速开始">README 快速开始</a></td>
|
||
</tr>
|
||
<tr>
|
||
<td>中文生产 ASR</td>
|
||
<td>Paraformer-Large</td>
|
||
<td>成熟中文 ASR 路径,可组合 VAD 和标点。</td>
|
||
<td><a href="https://www.funasr.com/docs/quickstart.html">教程</a></td>
|
||
</tr>
|
||
<tr>
|
||
<td>OpenAI API 示例中的英文路由</td>
|
||
<td><code>paraformer-en</code> alias</td>
|
||
<td>适合在 OpenAI 风格客户端里验证较轻量英文路径。</td>
|
||
<td><a href="https://www.funasr.com/docs/http-server.html">OpenAI API 示例</a></td>
|
||
</tr>
|
||
<tr>
|
||
<td>LLM-based ASR 或中文/英文/日语 + 方言实验</td>
|
||
<td>Fun-ASR-Nano</td>
|
||
<td>先评估 Python 路径;split-engine 与原生 vLLM 的加载契约不同。</td>
|
||
<td><a href="#vllm-checkpoint-paths">选择 vLLM 路径</a></td>
|
||
</tr>
|
||
<tr>
|
||
<td>离线长音频 ASR 与匿名说话人标签</td>
|
||
<td>MOSS-Transcribe-Diarize</td>
|
||
<td>一次离线请求返回转写、时间戳和录音内匿名说话人标签;不识别已知人物,也不需要外部 VAD 或说话人模型。</td>
|
||
<td><a href="https://www.funasr.com/docs/moss-transcribe-diarize.html">MOSS 部署指南</a></td>
|
||
</tr>
|
||
<tr>
|
||
<td>实时字幕或客服流式音频</td>
|
||
<td>Runtime WebSocket 服务</td>
|
||
<td>面向长连接流式会话和中间结果。</td>
|
||
<td><a href="https://www.funasr.com/docs/runtime-guide.html">Runtime 服务文档</a></td>
|
||
</tr>
|
||
<tr>
|
||
<td>录音归档批处理</td>
|
||
<td>SenseVoice-Small 或 Paraformer-Large</td>
|
||
<td>稳定离线转写路径;调用方负责 manifest、重试和日志。</td>
|
||
<td><a href="https://github.com/modelscope/FunASR/blob/main/examples/batch_asr_improved.py">批处理示例</a></td>
|
||
</tr>
|
||
<tr>
|
||
<td>从 Whisper/云端 ASR 迁移</td>
|
||
<td>先用 SenseVoice-Small,再 benchmark 其他模型</td>
|
||
<td>先建立强基线,再做模型专项调优。</td>
|
||
<td><a href="https://www.funasr.com/docs/migration.html">迁移指南</a></td>
|
||
</tr>
|
||
</tbody>
|
||
</table>
|
||
<span data-legacy-doc-anchor="openai-兼容-api-别名" id="aliases"></span><h2 id="openai-兼容-api-别名">OpenAI 兼容 API 别名</h2>
|
||
<p><code>examples/openai_api</code> 服务提供短别名,应用团队不需要了解具体模型仓库 ID:</p>
|
||
<ul>
|
||
<li><strong><code>sensevoice</code></strong> 使用 <code>iic/SenseVoiceSmall</code>,用于 CPU/GPU 多语种 HTTP 转写;返回文本已移除富文本标签。</li>
|
||
<li><strong><code>paraformer</code></strong> 使用 <code>paraformer-zh</code>,组合 VAD 和标点,适合评估中文转写。</li>
|
||
<li><strong><code>paraformer-en</code></strong> 使用 <code>paraformer-en</code>,组合 VAD,提供 OpenAI 风格客户端的英文转写路径。</li>
|
||
<li><strong><code>fun-asr-nano</code></strong> 使用 <code>FunAudioLLM/Fun-ASR-Nano-2512</code>,评估中文、英文、日语与中文方言/口音覆盖;测试 vLLM 加速时须选择兼容的运行路径。</li>
|
||
<li><strong><code>moss-transcribe-diarize</code></strong> 使用第三方 <code>OpenMOSS-Team/MOSS-Transcribe-Diarize</code>,用于离线转写和录音内匿名说话人标签。先按 <a href="https://www.funasr.com/docs/moss-transcribe-diarize.html">MOSS 指南</a> 准备独立依赖并审查远程代码;需要结构化分段时请求 <code>verbose_json</code>。它不需要外部 VAD/说话人模型,也不识别已知人物。</li>
|
||
</ul>
|
||
<p>这些别名属于加载 <code>AutoModel</code> 的<a href="https://github.com/modelscope/FunASR/blob/main/examples/openai_api/server.py">示例服务</a>,
|
||
不会配置原生 vLLM,也不会自动选择 <code>AutoModelVLLM</code>。
|
||
包内 <code>funasr-server</code> 有独立的加载与后端选择逻辑;不要跨服务直接套用别名或性能结果,
|
||
先核对对应的 <a href="https://www.funasr.com/docs/http-server.html">HTTP 指南</a>。</p>
|
||
<p>示例 HTTP 服务会清理顶层 <code>text</code> 和 <code>verbose_json</code> 中各分段的 <code>text</code>;
|
||
切换到该格式不会恢复情感/事件标签。需要原始标签时,请使用 Python SDK,
|
||
在展示后处理前保存返回的 <code>text</code>,参见<a href="https://www.funasr.com/docs/speaker-emotion.html">原始标签示例</a>。</p>
|
||
<p>如果部署目标是昇腾 NPU,请把 <code>fun-asr-nano</code> 和 SenseVoice / Paraformer 分开看。Fun-ASR-Nano 的 PyTorch <code>AutoModel</code> 路径在修复 NPU autocast 后已有 310P3 社区兼容性 smoke 结果,但该测试明显慢于 CPU;<code>AutoModelVLLM</code> 仍依赖 vLLM-Ascend 算子支持,并已遇到 Qwen3 rotary / <code>TransData</code> 失败。生产部署优先使用 CUDA/vLLM、标准 PyTorch CPU/GPU 或 GGUF runtime,除非你正在主动验证 Ascend 后端。</p>
|
||
<p>接入客户端前先检查在线服务:</p>
|
||
<pre id="code-2"><code class="language-bash">curl http://localhost:8000/v1/models
|
||
python examples/openai_api/smoke_test.py --base-url http://localhost:8000 --model sensevoice
|
||
</code></pre>
|
||
<p>SDK、JavaScript、工作流、Postman、OpenAPI、Docker 和 Kubernetes 路径可从 <a href="https://www.funasr.com/docs/http-server.html">OpenAI API 示例</a> 开始。</p>
|
||
<span data-legacy-doc-anchor="按工作负载选择运行路径" id="runtime"></span><h2 id="按工作负载选择运行路径">按工作负载选择运行路径</h2>
|
||
<table>
|
||
<thead>
|
||
<tr>
|
||
<th>工作负载</th>
|
||
<th>运行路径</th>
|
||
<th>说明</th>
|
||
</tr>
|
||
</thead>
|
||
<tbody>
|
||
<tr>
|
||
<td>Notebook 或一次性评估</td>
|
||
<td>Python <code>AutoModel</code></td>
|
||
<td>验证安装、模型下载和输出结构的最短路径。</td>
|
||
</tr>
|
||
<tr>
|
||
<td>内部 HTTP 服务</td>
|
||
<td>OpenAI 兼容 API</td>
|
||
<td>复用 OpenAI 风格客户端、Dify、n8n、LangChain、AutoGen 和 HTTP 节点。</td>
|
||
</tr>
|
||
<tr>
|
||
<td>可复现本地容器 demo</td>
|
||
<td>Docker Compose API</td>
|
||
<td>CPU-first smoke test;使用 CUDA 前先适配镜像。</td>
|
||
</tr>
|
||
<tr>
|
||
<td>集群内私有服务</td>
|
||
<td>Kubernetes API 模板</td>
|
||
<td>私有 <code>ClusterIP</code>、持久化模型缓存、<code>/health</code> probes 和 port-forward smoke test。</td>
|
||
</tr>
|
||
<tr>
|
||
<td>实时音频</td>
|
||
<td>Runtime WebSocket 服务</td>
|
||
<td>用真实音频验证 chunk size、VAD、断句、重连和客户端背压。</td>
|
||
</tr>
|
||
<tr>
|
||
<td>LLM-based ASR 吞吐</td>
|
||
<td>在下方选择 split-engine 或原生 vLLM</td>
|
||
<td>同时匹配 checkpoint、加载接口和已测环境;这不是 Paraformer 后端。</td>
|
||
</tr>
|
||
</tbody>
|
||
</table>
|
||
<p>选择部署方式时可以参考 <a href="https://www.funasr.com/docs/deployment-matrix.html">部署选型表</a>。</p>
|
||
<p><a id="vllm-checkpoint-paths"></a></p>
|
||
<h2 id="选择-vllm-权重与接口">选择 vLLM 权重与接口</h2>
|
||
<table>
|
||
<thead>
|
||
<tr>
|
||
<th>路径</th>
|
||
<th>权重与接口</th>
|
||
<th>下一步</th>
|
||
</tr>
|
||
</thead>
|
||
<tbody>
|
||
<tr>
|
||
<td>FunASR split-engine</td>
|
||
<td>基础 <code>FunAudioLLM/Fun-ASR-Nano-2512</code> 资产,由 <code>AutoModelVLLM</code> 加载;FunASR 处理音频部分,vLLM 处理解码器。</td>
|
||
<td><a href="https://www.funasr.com/docs/vllm.html">Split-engine 准备与边界</a></td>
|
||
</tr>
|
||
<tr>
|
||
<td>官方原生 vLLM</td>
|
||
<td>转换后的 <code>FunAudioLLM/Fun-ASR-Nano-2512-vllm</code> 快照,通过 vLLM 原生模型实现和 <code>/v1/audio/transcriptions</code> 提供服务;不是 <code>AutoModelVLLM</code> 加载。</td>
|
||
<td><a href="https://www.funasr.com/docs/official-native-vllm.html">官方功能验证</a></td>
|
||
</tr>
|
||
<tr>
|
||
<td>历史社区原生 vLLM</td>
|
||
<td>社区 <code>allendou/Fun-ASR-Nano-2512-vllm</code>,测试日期 2026-08-13;耗时只属于当时的权重与环境。</td>
|
||
<td><a href="https://www.funasr.com/docs/native-vllm.html">历史社区记录</a></td>
|
||
</tr>
|
||
</tbody>
|
||
</table>
|
||
<p>官方记录固定了模型 revision 和既有环境,不是全新安装配方、持续负载性能评测,
|
||
也不是 <code>/v1/realtime</code> 流式验证。不要把社区历史耗时用于官方模型。
|
||
MOSS 请遵循其独立部署指南:以上 Nano 权重和验证不能证明 MOSS 的运行时兼容性。
|
||
先一起确定模型、权重、接口与环境,再评估自己的工作负载。</p>
|
||
<span data-legacy-doc-anchor="上线前先-benchmark" id="benchmark"></span><h2 id="上线前先-benchmark">上线前先 benchmark</h2>
|
||
<p>不要只用一个干净 demo 文件选型。先准备一个小而有代表性的集合:</p>
|
||
<ul>
|
||
<li>20-50 条音频,覆盖短音频、长会议、静音、噪声、多人重叠、领域词汇和目标语言。</li>
|
||
<li>记录模型名、模型版本、FunASR 版本、设备、CPU/GPU 型号、CUDA/PyTorch 版本、运行路径、batch size,以及是否排除 warmup/模型下载时间。</li>
|
||
<li>使用你已有的 WER/CER 流程或人工审阅,不要只看转写文本是否“读起来还行”。</li>
|
||
<li>同时记录延迟、吞吐、内存、失败样例和上传大小限制。</li>
|
||
<li>保留至少一个公开样例用于 smoke test,也保留至少一个真实私有样本用于部署验证。</li>
|
||
</ul>
|
||
<p>迁移场景可以使用 <a href="https://github.com/modelscope/FunASR/blob/main/examples/migration">迁移评测示例</a> 和 <a href="https://www.funasr.com/docs/migration.html">迁移指南</a>。</p>
|
||
<h2 id="实用建议">实用建议</h2>
|
||
<ul>
|
||
<li>demo、私有 API、Agent 语音输入和多语种场景优先试 SenseVoice-Small。</li>
|
||
<li>中文生产流量优先试 Paraformer,尤其是希望走成熟非自回归 ASR 路径时。</li>
|
||
<li>明确需要 LLM-based 模型路径或 vLLM 加速实验时,再试 Fun-ASR-Nano;如需单独的 31 语种覆盖,请改用 Fun-ASR-MLT-Nano。</li>
|
||
<li>离线长录音需要同一次请求给出录音内匿名说话人标签时,使用 MOSS-Transcribe-Diarize;它不是实时 WebSocket 或已知人物身份识别路径。</li>
|
||
<li>需要中间结果和长连接时,优先使用 streaming runtime,而不是普通 HTTP 转写接口。</li>
|
||
<li>生产 runbook 中固定模型 alias,保证 benchmark 和问题复现可追踪。</li>
|
||
<li>遇到阻塞时,用 <a href="https://github.com/modelscope/FunASR/issues/new?template=deployment_help.md">Deployment Help issue</a> 提供模型、设备、命令、日志、音频时长和运行路径。</li>
|
||
</ul></article>
|
||
<nav aria-label="相邻文档" class="docs-next">
|
||
<a href="https://www.funasr.com/docs/python-api.html">← Python SDK: AutoModel</a><a href="https://www.funasr.com/docs/command-line.html">命令行转写 →</a> </nav>
|
||
</div>
|
||
<aside class="docs-toc"><strong>本页目录</strong><div class="toc">
|
||
<ul>
|
||
<li><a href="#funasr-模型选择指南">FunASR 模型选择指南</a><ul>
|
||
<li><a href="#先用-transformers-体验-nano">先用 Transformers 体验 Nano</a></li>
|
||
<li><a href="#默认快速路径">默认快速路径</a></li>
|
||
<li><a href="#决策表">决策表</a></li>
|
||
<li><a href="#openai-兼容-api-别名">OpenAI 兼容 API 别名</a></li>
|
||
<li><a href="#按工作负载选择运行路径">按工作负载选择运行路径</a></li>
|
||
<li><a href="#选择-vllm-权重与接口">选择 vLLM 权重与接口</a></li>
|
||
<li><a href="#上线前先-benchmark">上线前先 benchmark</a></li>
|
||
<li><a href="#实用建议">实用建议</a></li>
|
||
</ul>
|
||
</li>
|
||
</ul>
|
||
</div>
|
||
</aside></div>
|
||
</main>
|
||
<footer class="site-footer">
|
||
<div>
|
||
<strong>FunASR</strong>
|
||
<p>面向生产部署的开源语音基础设施。</p>
|
||
</div>
|
||
<nav aria-label="官方仓库" class="footer-repositories" data-footer-repositories="">
|
||
<strong>官方仓库</strong>
|
||
<div class="footer-links">
|
||
<a href="https://www.funasr.com/go/fun-asr">Fun-ASR</a>
|
||
<a href="https://www.funasr.com/go/sensevoice">SenseVoice</a>
|
||
<a href="https://www.funasr.com/go/funclip">FunClip</a>
|
||
</div>
|
||
</nav>
|
||
<div class="footer-links">
|
||
<a href="https://www.funasr.com/deploy/">部署</a>
|
||
<a href="https://www.funasr.com/docs/">文档</a>
|
||
<a href="https://www.funasr.com/go/releases">发布</a>
|
||
<a href="https://www.funasr.com/donors.html">功德榜</a>
|
||
</div>
|
||
</footer>
|
||
<script defer="" src="../assets/js/site.d446f5fbcfe2.js"></script>
|
||
<script defer="" src="../assets/js/experience.3f688a12942a.js"></script>
|
||
</body>
|
||
</html>
|