mirror of
https://github.com/k2-fsa/icefall.git
synced 2025-08-09 18:12:19 +00:00
157 lines
8.5 KiB
HTML
157 lines
8.5 KiB
HTML
|
|
|
|
<!DOCTYPE html>
|
|
<html class="writer-html5" lang="en">
|
|
<head>
|
|
<meta charset="utf-8" /><meta name="viewport" content="width=device-width, initial-scale=1" />
|
|
|
|
<meta name="viewport" content="width=device-width, initial-scale=1.0" />
|
|
<title>FST-based forced alignment — icefall 0.1 documentation</title>
|
|
<link rel="stylesheet" type="text/css" href="../_static/pygments.css?v=fa44fd50" />
|
|
<link rel="stylesheet" type="text/css" href="../_static/css/theme.css?v=7ab3649f" />
|
|
|
|
|
|
<script src="../_static/jquery.js?v=5d32c60e"></script>
|
|
<script src="../_static/_sphinx_javascript_frameworks_compat.js?v=2cd50e6c"></script>
|
|
<script data-url_root="../" id="documentation_options" src="../_static/documentation_options.js?v=e031e9a9"></script>
|
|
<script src="../_static/doctools.js?v=888ff710"></script>
|
|
<script src="../_static/sphinx_highlight.js?v=4825356b"></script>
|
|
<script src="../_static/js/theme.js"></script>
|
|
<link rel="index" title="Index" href="../genindex.html" />
|
|
<link rel="search" title="Search" href="../search.html" />
|
|
<link rel="next" title="Two approaches" href="diff.html" />
|
|
<link rel="prev" title="Export LSTM transducer models to ncnn" href="../model-export/export-ncnn-lstm.html" />
|
|
</head>
|
|
|
|
<body class="wy-body-for-nav">
|
|
<div class="wy-grid-for-nav">
|
|
<nav data-toggle="wy-nav-shift" class="wy-nav-side">
|
|
<div class="wy-side-scroll">
|
|
<div class="wy-side-nav-search" >
|
|
|
|
|
|
|
|
<a href="../index.html" class="icon icon-home">
|
|
icefall
|
|
</a>
|
|
<div role="search">
|
|
<form id="rtd-search-form" class="wy-form" action="../search.html" method="get">
|
|
<input type="text" name="q" placeholder="Search docs" aria-label="Search docs" />
|
|
<input type="hidden" name="check_keywords" value="yes" />
|
|
<input type="hidden" name="area" value="default" />
|
|
</form>
|
|
</div>
|
|
</div><div class="wy-menu wy-menu-vertical" data-spy="affix" role="navigation" aria-label="Navigation menu">
|
|
<p class="caption" role="heading"><span class="caption-text">Contents:</span></p>
|
|
<ul class="current">
|
|
<li class="toctree-l1"><a class="reference internal" href="../for-dummies/index.html">Icefall for dummies tutorial</a></li>
|
|
<li class="toctree-l1"><a class="reference internal" href="../installation/index.html">Installation</a></li>
|
|
<li class="toctree-l1"><a class="reference internal" href="../docker/index.html">Docker</a></li>
|
|
<li class="toctree-l1"><a class="reference internal" href="../faqs.html">Frequently Asked Questions (FAQs)</a></li>
|
|
<li class="toctree-l1"><a class="reference internal" href="../model-export/index.html">Model export</a></li>
|
|
<li class="toctree-l1 current"><a class="current reference internal" href="#">FST-based forced alignment</a><ul>
|
|
<li class="toctree-l2"><a class="reference internal" href="diff.html">Two approaches</a></li>
|
|
<li class="toctree-l2"><a class="reference internal" href="kaldi-based.html">Kaldi-based forced alignment</a></li>
|
|
<li class="toctree-l2"><a class="reference internal" href="k2-based.html">k2-based forced alignment</a></li>
|
|
</ul>
|
|
</li>
|
|
</ul>
|
|
<ul>
|
|
<li class="toctree-l1"><a class="reference internal" href="../recipes/index.html">Recipes</a></li>
|
|
</ul>
|
|
<ul>
|
|
<li class="toctree-l1"><a class="reference internal" href="../contributing/index.html">Contributing</a></li>
|
|
<li class="toctree-l1"><a class="reference internal" href="../huggingface/index.html">Huggingface</a></li>
|
|
</ul>
|
|
<ul>
|
|
<li class="toctree-l1"><a class="reference internal" href="../decoding-with-langugage-models/index.html">Decoding with language models</a></li>
|
|
</ul>
|
|
|
|
</div>
|
|
</div>
|
|
</nav>
|
|
|
|
<section data-toggle="wy-nav-shift" class="wy-nav-content-wrap"><nav class="wy-nav-top" aria-label="Mobile navigation menu" >
|
|
<i data-toggle="wy-nav-top" class="fa fa-bars"></i>
|
|
<a href="../index.html">icefall</a>
|
|
</nav>
|
|
|
|
<div class="wy-nav-content">
|
|
<div class="rst-content">
|
|
<div role="navigation" aria-label="Page navigation">
|
|
<ul class="wy-breadcrumbs">
|
|
<li><a href="../index.html" class="icon icon-home" aria-label="Home"></a></li>
|
|
<li class="breadcrumb-item active">FST-based forced alignment</li>
|
|
<li class="wy-breadcrumbs-aside">
|
|
<a href="https://github.com/k2-fsa/icefall/blob/master/docs/source/fst-based-forced-alignment/index.rst" class="fa fa-github"> Edit on GitHub</a>
|
|
</li>
|
|
</ul>
|
|
<hr/>
|
|
</div>
|
|
<div role="main" class="document" itemscope="itemscope" itemtype="http://schema.org/Article">
|
|
<div itemprop="articleBody">
|
|
|
|
<section id="fst-based-forced-alignment">
|
|
<h1>FST-based forced alignment<a class="headerlink" href="#fst-based-forced-alignment" title="Permalink to this heading"></a></h1>
|
|
<p>This section describes how to perform <strong>FST-based</strong> <code class="docutils literal notranslate"><span class="pre">forced</span> <span class="pre">alignment</span></code> with models
|
|
trained by <a class="reference external" href="https://www.cs.toronto.edu/~graves/icml_2006.pdf">CTC</a> loss.</p>
|
|
<p>We use <a class="reference external" href="https://pytorch.org/audio/main/tutorials/ctc_forced_alignment_api_tutorial.html">CTC FORCED ALIGNMENT API TUTORIAL</a>
|
|
from <a class="reference external" href="https://github.com/pytorch/audio">torchaudio</a> as a reference in this section.</p>
|
|
<p>Different from <a class="reference external" href="https://github.com/pytorch/audio">torchaudio</a>, we use an <code class="docutils literal notranslate"><span class="pre">FST</span></code>-based approach.</p>
|
|
<div class="toctree-wrapper compound">
|
|
<p class="caption" role="heading"><span class="caption-text">Contents:</span></p>
|
|
<ul>
|
|
<li class="toctree-l1"><a class="reference internal" href="diff.html">Two approaches</a><ul>
|
|
<li class="toctree-l2"><a class="reference internal" href="diff.html#differences-between-the-two-approaches">Differences between the two approaches</a></li>
|
|
</ul>
|
|
</li>
|
|
<li class="toctree-l1"><a class="reference internal" href="kaldi-based.html">Kaldi-based forced alignment</a><ul>
|
|
<li class="toctree-l2"><a class="reference internal" href="kaldi-based.html#prepare-the-environment">Prepare the environment</a></li>
|
|
<li class="toctree-l2"><a class="reference internal" href="kaldi-based.html#get-the-test-data">Get the test data</a></li>
|
|
<li class="toctree-l2"><a class="reference internal" href="kaldi-based.html#compute-log-probs">Compute log_probs</a></li>
|
|
<li class="toctree-l2"><a class="reference internal" href="kaldi-based.html#create-token2id-and-id2token">Create token2id and id2token</a></li>
|
|
<li class="toctree-l2"><a class="reference internal" href="kaldi-based.html#create-word2id-and-id2word">Create word2id and id2word</a></li>
|
|
<li class="toctree-l2"><a class="reference internal" href="kaldi-based.html#generate-lexicon-related-files">Generate lexicon-related files</a></li>
|
|
<li class="toctree-l2"><a class="reference internal" href="kaldi-based.html#convert-transcript-to-an-fst-graph">Convert transcript to an FST graph</a></li>
|
|
<li class="toctree-l2"><a class="reference internal" href="kaldi-based.html#force-aligner">Force aligner</a></li>
|
|
<li class="toctree-l2"><a class="reference internal" href="kaldi-based.html#segment-each-word-using-the-computed-alignments">Segment each word using the computed alignments</a></li>
|
|
<li class="toctree-l2"><a class="reference internal" href="kaldi-based.html#summary">Summary</a></li>
|
|
</ul>
|
|
</li>
|
|
<li class="toctree-l1"><a class="reference internal" href="k2-based.html">k2-based forced alignment</a></li>
|
|
</ul>
|
|
</div>
|
|
</section>
|
|
|
|
|
|
</div>
|
|
</div>
|
|
<footer><div class="rst-footer-buttons" role="navigation" aria-label="Footer">
|
|
<a href="../model-export/export-ncnn-lstm.html" class="btn btn-neutral float-left" title="Export LSTM transducer models to ncnn" accesskey="p" rel="prev"><span class="fa fa-arrow-circle-left" aria-hidden="true"></span> Previous</a>
|
|
<a href="diff.html" class="btn btn-neutral float-right" title="Two approaches" accesskey="n" rel="next">Next <span class="fa fa-arrow-circle-right" aria-hidden="true"></span></a>
|
|
</div>
|
|
|
|
<hr/>
|
|
|
|
<div role="contentinfo">
|
|
<p>© Copyright 2021, icefall development team.</p>
|
|
</div>
|
|
|
|
Built with <a href="https://www.sphinx-doc.org/">Sphinx</a> using a
|
|
<a href="https://github.com/readthedocs/sphinx_rtd_theme">theme</a>
|
|
provided by <a href="https://readthedocs.org">Read the Docs</a>.
|
|
|
|
|
|
</footer>
|
|
</div>
|
|
</div>
|
|
</section>
|
|
</div>
|
|
<script>
|
|
jQuery(function () {
|
|
SphinxRtdTheme.Navigation.enable(true);
|
|
});
|
|
</script>
|
|
|
|
</body>
|
|
</html> |