readme_zh.html 15 KB

123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124125126127128129130131132133134135136137138139140141142143144145146147148149150151152153154155156157158159160161162163164165166167168169170171172173174175176177178179180181182183184185186187188189190191192193194195196197198199200201202203204205206207208209210211212213214215216217218219220221222223224225226227228229230231232233234235236
  1. <!DOCTYPE html>
  2. <html class="writer-html5" lang="en" >
  3. <head>
  4. <meta charset="utf-8" />
  5. <meta name="viewport" content="width=device-width, initial-scale=1.0" />
  6. <title>FunASR离线文件转写服务开发指南(点击此处) &mdash; FunASR documentation</title><link rel="stylesheet" href="../../_static/css/theme.css" type="text/css" />
  7. <link rel="stylesheet" href="../../_static/pygments.css" type="text/css" />
  8. <!--[if lt IE 9]>
  9. <script src="../../_static/js/html5shiv.min.js"></script>
  10. <![endif]-->
  11. <script id="documentation_options" data-url_root="../../" src="../../_static/documentation_options.js"></script>
  12. <script src="../../_static/jquery.js"></script>
  13. <script src="../../_static/underscore.js"></script>
  14. <script src="../../_static/doctools.js"></script>
  15. <script src="../../_static/language_data.js"></script>
  16. <script crossorigin="anonymous" integrity="sha256-Ae2Vz/4ePdIu6ZyI/5ZGsYnb+m0JlOmKPjt6XZ9JJkA=" src="https://cdnjs.cloudflare.com/ajax/libs/require.js/2.3.4/require.min.js"></script>
  17. <script src="../../_static/js/theme.js"></script>
  18. <link rel="index" title="Index" href="../../genindex.html" />
  19. <link rel="search" title="Search" href="../../search.html" />
  20. </head>
  21. <body class="wy-body-for-nav">
  22. <div class="wy-grid-for-nav">
  23. <nav data-toggle="wy-nav-shift" class="wy-nav-side">
  24. <div class="wy-side-scroll">
  25. <div class="wy-side-nav-search" >
  26. <a href="../../index.html" class="icon icon-home">
  27. FunASR
  28. </a>
  29. <div role="search">
  30. <form id="rtd-search-form" class="wy-form" action="../../search.html" method="get">
  31. <input type="text" name="q" placeholder="Search docs" aria-label="Search docs" />
  32. <input type="hidden" name="check_keywords" value="yes" />
  33. <input type="hidden" name="area" value="default" />
  34. </form>
  35. </div>
  36. </div><div class="wy-menu wy-menu-vertical" data-spy="affix" role="navigation" aria-label="Navigation menu">
  37. <p class="caption"><span class="caption-text">Installation</span></p>
  38. <ul>
  39. <li class="toctree-l1"><a class="reference internal" href="../../installation/installation.html">Installation</a></li>
  40. <li class="toctree-l1"><a class="reference internal" href="../../installation/docker.html">Docker</a></li>
  41. </ul>
  42. <p class="caption"><span class="caption-text">Quick Start</span></p>
  43. <ul>
  44. <li class="toctree-l1"><a class="reference internal" href="../../funasr/quick_start.html">Quick Start</a></li>
  45. </ul>
  46. <p class="caption"><span class="caption-text">Academic Egs</span></p>
  47. <ul>
  48. <li class="toctree-l1"><a class="reference internal" href="../../academic_recipe/asr_recipe.html">Speech Recognition</a></li>
  49. <li class="toctree-l1"><a class="reference internal" href="../../academic_recipe/punc_recipe.html">Punctuation Restoration</a></li>
  50. <li class="toctree-l1"><a class="reference internal" href="../../academic_recipe/vad_recipe.html">Voice Activity Detection</a></li>
  51. <li class="toctree-l1"><a class="reference internal" href="../../academic_recipe/sv_recipe.html">Speaker Verification</a></li>
  52. <li class="toctree-l1"><a class="reference internal" href="../../academic_recipe/sd_recipe.html">Speaker Diarization</a></li>
  53. </ul>
  54. <p class="caption"><span class="caption-text">ModelScope Egs</span></p>
  55. <ul>
  56. <li class="toctree-l1"><a class="reference internal" href="../../modelscope_pipeline/quick_start.html">Quick Start</a></li>
  57. <li class="toctree-l1"><a class="reference internal" href="../../egs_modelscope/asr/TEMPLATE/README.html">Speech Recognition</a></li>
  58. <li class="toctree-l1"><a class="reference internal" href="../../egs_modelscope/vad/TEMPLATE/README.html">Voice Activity Detection</a></li>
  59. <li class="toctree-l1"><a class="reference internal" href="../../egs_modelscope/punctuation/TEMPLATE/README.html">Punctuation Restoration</a></li>
  60. <li class="toctree-l1"><a class="reference internal" href="../../egs_modelscope/tp/TEMPLATE/README.html">Timestamp Prediction (FA)</a></li>
  61. <li class="toctree-l1"><a class="reference internal" href="../../modelscope_pipeline/sv_pipeline.html">Speaker Verification</a></li>
  62. <li class="toctree-l1"><a class="reference internal" href="../../modelscope_pipeline/sd_pipeline.html">Speaker Diarization</a></li>
  63. <li class="toctree-l1"><a class="reference internal" href="../../modelscope_pipeline/itn_pipeline.html">Inverse Text Normalization (ITN)</a></li>
  64. </ul>
  65. <p class="caption"><span class="caption-text">Model Zoo</span></p>
  66. <ul>
  67. <li class="toctree-l1"><a class="reference internal" href="../../model_zoo/modelscope_models.html">Pretrained Models Released on ModelScope</a></li>
  68. <li class="toctree-l1"><a class="reference internal" href="../../model_zoo/huggingface_models.html">Pretrained Models on Huggingface</a></li>
  69. </ul>
  70. <p class="caption"><span class="caption-text">Runtime and Service</span></p>
  71. <ul>
  72. <li class="toctree-l1"><a class="reference internal" href="../readme.html">FunASR Runtime Roadmap</a></li>
  73. <li class="toctree-l1"><a class="reference internal" href="../docs/SDK_tutorial_online.html">FunASR Realtime Transcribe Service</a></li>
  74. <li class="toctree-l1"><a class="reference internal" href="../docs/SDK_tutorial.html">Highlights</a></li>
  75. <li class="toctree-l1"><a class="reference internal" href="../docs/SDK_tutorial.html#funasr-offline-file-transcription-service">FunASR Offline File Transcription Service</a></li>
  76. <li class="toctree-l1"><a class="reference internal" href="../html5/readme.html">Speech Recognition Service Html5 Client Access Interface</a></li>
  77. </ul>
  78. <p class="caption"><span class="caption-text">Benchmark and Leaderboard</span></p>
  79. <ul>
  80. <li class="toctree-l1"><a class="reference internal" href="../../benchmark/benchmark_pipeline_cer.html">Leaderboard IO</a></li>
  81. </ul>
  82. <p class="caption"><span class="caption-text">Funasr Library</span></p>
  83. <ul>
  84. <li class="toctree-l1"><a class="reference internal" href="../../reference/build_task.html">Build custom tasks</a></li>
  85. </ul>
  86. <p class="caption"><span class="caption-text">Papers</span></p>
  87. <ul>
  88. <li class="toctree-l1"><a class="reference internal" href="../../reference/papers.html">Papers</a></li>
  89. </ul>
  90. <p class="caption"><span class="caption-text">Application</span></p>
  91. <ul>
  92. <li class="toctree-l1"><a class="reference internal" href="../../reference/application.html">Audio Cut</a></li>
  93. <li class="toctree-l1"><a class="reference internal" href="../../reference/application.html#realtime-speech-recognition">Realtime Speech Recognition</a></li>
  94. <li class="toctree-l1"><a class="reference internal" href="../../reference/application.html#audio-chat">Audio Chat</a></li>
  95. </ul>
  96. <p class="caption"><span class="caption-text">FQA</span></p>
  97. <ul>
  98. <li class="toctree-l1"><a class="reference internal" href="../../reference/FQA.html">FQA</a></li>
  99. </ul>
  100. </div>
  101. </div>
  102. </nav>
  103. <section data-toggle="wy-nav-shift" class="wy-nav-content-wrap"><nav class="wy-nav-top" aria-label="Mobile navigation menu" >
  104. <i data-toggle="wy-nav-top" class="fa fa-bars"></i>
  105. <a href="../../index.html">FunASR</a>
  106. </nav>
  107. <div class="wy-nav-content">
  108. <div class="rst-content">
  109. <div role="navigation" aria-label="Page navigation">
  110. <ul class="wy-breadcrumbs">
  111. <li><a href="../../index.html" class="icon icon-home" aria-label="Home"></a></li>
  112. <li class="breadcrumb-item active">FunASR离线文件转写服务开发指南(点击此处)</li>
  113. <li class="wy-breadcrumbs-aside">
  114. <a href="../../_sources/runtime/websocket/readme_zh.md.txt" rel="nofollow"> View page source</a>
  115. </li>
  116. </ul>
  117. <hr/>
  118. </div>
  119. <div role="main" class="document" itemscope="itemscope" itemtype="http://schema.org/Article">
  120. <div itemprop="articleBody">
  121. <div class="section" id="funasr">
  122. <h1>FunASR离线文件转写服务开发指南(<a class="reference internal" href="../docs/SDK_advanced_guide_offline_zh.html"><span class="doc">点击此处</span></a>)<a class="headerlink" href="#funasr" title="Permalink to this headline"></a></h1>
  123. </div>
  124. <div class="section" id="id1">
  125. <h1>FunASR实时语音听写服务开发指南(<a class="reference internal" href="../docs/SDK_advanced_guide_online_zh.html"><span class="doc">点击此处</span></a>)<a class="headerlink" href="#id1" title="Permalink to this headline"></a></h1>
  126. </div>
  127. <div class="section" id="id2">
  128. <h1>如果您想自己编译文件,可以参考下述步骤<a class="headerlink" href="#id2" title="Permalink to this headline"></a></h1>
  129. <div class="section" id="linux-unix">
  130. <h2>Linux/Unix 平台编译<a class="headerlink" href="#linux-unix" title="Permalink to this headline"></a></h2>
  131. <div class="section" id="onnxruntime">
  132. <h3>下载 onnxruntime<a class="headerlink" href="#onnxruntime" title="Permalink to this headline"></a></h3>
  133. <div class="highlight-shell notranslate"><div class="highlight"><pre><span></span>wget https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/dep_libs/onnxruntime-linux-x64-1.14.0.tgz
  134. tar -zxvf onnxruntime-linux-x64-1.14.0.tgz
  135. </pre></div>
  136. </div>
  137. </div>
  138. <div class="section" id="ffmpeg">
  139. <h3>下载 ffmpeg<a class="headerlink" href="#ffmpeg" title="Permalink to this headline"></a></h3>
  140. <div class="highlight-shell notranslate"><div class="highlight"><pre><span></span>wget https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/dep_libs/ffmpeg-master-latest-linux64-gpl-shared.tar.xz
  141. tar -xvf ffmpeg-master-latest-linux64-gpl-shared.tar.xz
  142. </pre></div>
  143. </div>
  144. </div>
  145. <div class="section" id="id3">
  146. <h3>安装依赖<a class="headerlink" href="#id3" title="Permalink to this headline"></a></h3>
  147. <div class="highlight-shell notranslate"><div class="highlight"><pre><span></span><span class="c1"># openblas</span>
  148. sudo apt-get install libopenblas-dev <span class="c1">#ubuntu</span>
  149. <span class="c1"># sudo yum -y install openblas-devel #centos</span>
  150. <span class="c1"># openssl</span>
  151. apt-get install libssl-dev <span class="c1">#ubuntu </span>
  152. <span class="c1"># yum install openssl-devel #centos</span>
  153. </pre></div>
  154. </div>
  155. </div>
  156. <div class="section" id="runtime">
  157. <h3>编译 runtime<a class="headerlink" href="#runtime" title="Permalink to this headline"></a></h3>
  158. <div class="highlight-shell notranslate"><div class="highlight"><pre><span></span>git clone https://github.com/alibaba-damo-academy/FunASR.git <span class="o">&amp;&amp;</span> <span class="nb">cd</span> FunASR/runtime/websocket
  159. mkdir build <span class="o">&amp;&amp;</span> <span class="nb">cd</span> build
  160. cmake -DCMAKE_BUILD_TYPE<span class="o">=</span>release .. -DONNXRUNTIME_DIR<span class="o">=</span>/path/to/onnxruntime-linux-x64-1.14.0 -DFFMPEG_DIR<span class="o">=</span>/path/to/ffmpeg-master-latest-linux64-gpl-shared
  161. make -j <span class="m">4</span>
  162. </pre></div>
  163. </div>
  164. </div>
  165. </div>
  166. <div class="section" id="windows">
  167. <h2>Windows 平台编译<a class="headerlink" href="#windows" title="Permalink to this headline"></a></h2>
  168. <div class="section" id="id4">
  169. <h3>下载 onnxruntime<a class="headerlink" href="#id4" title="Permalink to this headline"></a></h3>
  170. <p>https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/dep_libs/onnxruntime-win-x64-1.16.1.zip</p>
  171. <p>下载并解压到 d:/ffmpeg-master-latest-win64-gpl-shared</p>
  172. </div>
  173. <div class="section" id="id5">
  174. <h3>下载 ffmpeg<a class="headerlink" href="#id5" title="Permalink to this headline"></a></h3>
  175. <p>https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/dep_libs/ffmpeg-master-latest-win64-gpl-shared.zip</p>
  176. <p>下载并解压到 d:/onnxruntime-win-x64-1.16.1</p>
  177. </div>
  178. <div class="section" id="openssl">
  179. <h3>编译 openssl<a class="headerlink" href="#openssl" title="Permalink to this headline"></a></h3>
  180. <p>https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/dep_libs/openssl-1.1.1w.zip</p>
  181. <p>下载解压到 d:/openssl-1.1.1w</p>
  182. </div>
  183. <div class="section" id="id6">
  184. <h3>编译 runtime<a class="headerlink" href="#id6" title="Permalink to this headline"></a></h3>
  185. <div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="n">git</span> <span class="n">clone</span> <span class="n">https</span><span class="p">:</span><span class="o">//</span><span class="n">github</span><span class="o">.</span><span class="n">com</span><span class="o">/</span><span class="n">alibaba</span><span class="o">-</span><span class="n">damo</span><span class="o">-</span><span class="n">academy</span><span class="o">/</span><span class="n">FunASR</span><span class="o">.</span><span class="n">git</span>
  186. <span class="n">cd</span> <span class="n">FunASR</span><span class="o">/</span><span class="n">runtime</span><span class="o">/</span><span class="n">websocket</span>
  187. <span class="n">mkdir</span> <span class="n">build</span>
  188. <span class="n">cd</span> <span class="n">build</span>
  189. <span class="n">cmake</span> <span class="o">../</span> <span class="o">-</span><span class="n">D</span> <span class="n">OPENSSL_ROOT_DIR</span><span class="o">=</span><span class="n">d</span><span class="p">:</span><span class="o">/</span><span class="n">openssl</span><span class="o">-</span><span class="mf">1.1</span><span class="o">.</span><span class="mi">1</span><span class="n">w</span> <span class="o">-</span><span class="n">D</span> <span class="n">FFMPEG_DIR</span><span class="o">=</span><span class="n">d</span><span class="p">:</span><span class="o">/</span><span class="n">ffmpeg</span><span class="o">-</span><span class="n">master</span><span class="o">-</span><span class="n">latest</span><span class="o">-</span><span class="n">win64</span><span class="o">-</span><span class="n">gpl</span><span class="o">-</span><span class="n">shared</span> <span class="o">-</span><span class="n">D</span> <span class="n">ONNXRUNTIME_DIR</span><span class="o">=</span><span class="n">d</span><span class="p">:</span><span class="o">/</span><span class="n">onnxruntime</span><span class="o">-</span><span class="n">win</span><span class="o">-</span><span class="n">x64</span><span class="o">-</span><span class="mf">1.16</span><span class="o">.</span><span class="mi">1</span>
  190. </pre></div>
  191. </div>
  192. <p>Visual Studio 打开 FunASR/runtime/websocket/build/FunASRWebscoket.sln 完成编译;
  193. 编译后的可执行文件位于:FunASR/runtime/websocket/build/bin/Debug;
  194. 从 onnxruntime-win-x64-1.16.1/lib, ffmpeg-master-latest-win64-gpl-shared/bin, openssl-1.1.1w/bin copy相关的DLL库至: FunASR/runtime/websocket/build/bin/Debug</p>
  195. </div>
  196. </div>
  197. </div>
  198. </div>
  199. </div>
  200. <footer>
  201. <hr/>
  202. <div role="contentinfo">
  203. <p>&#169; Copyright 2022, Speech Lab, Alibaba Group.</p>
  204. </div>
  205. Built with <a href="https://www.sphinx-doc.org/">Sphinx</a> using a
  206. <a href="https://github.com/readthedocs/sphinx_rtd_theme">theme</a>
  207. provided by <a href="https://readthedocs.org">Read the Docs</a>.
  208. </footer>
  209. </div>
  210. </div>
  211. </section>
  212. </div>
  213. <script>
  214. jQuery(function () {
  215. SphinxRtdTheme.Navigation.enable(true);
  216. });
  217. </script>
  218. </body>
  219. </html>