mirror of
https://github.com/k2-fsa/icefall.git
synced 2025-08-09 18:12:19 +00:00
260 lines
13 KiB
HTML
260 lines
13 KiB
HTML
<!DOCTYPE html>
|
|
<html class="writer-html5" lang="en" >
|
|
<head>
|
|
<meta charset="utf-8" /><meta name="generator" content="Docutils 0.17.1: http://docutils.sourceforge.net/" />
|
|
|
|
<meta name="viewport" content="width=device-width, initial-scale=1.0" />
|
|
<title>How to create a recipe — icefall 0.1 documentation</title>
|
|
<link rel="stylesheet" href="../_static/pygments.css" type="text/css" />
|
|
<link rel="stylesheet" href="../_static/css/theme.css" type="text/css" />
|
|
<!--[if lt IE 9]>
|
|
<script src="../_static/js/html5shiv.min.js"></script>
|
|
<![endif]-->
|
|
|
|
<script data-url_root="../" id="documentation_options" src="../_static/documentation_options.js"></script>
|
|
<script src="../_static/jquery.js"></script>
|
|
<script src="../_static/underscore.js"></script>
|
|
<script src="../_static/_sphinx_javascript_frameworks_compat.js"></script>
|
|
<script src="../_static/doctools.js"></script>
|
|
<script src="../_static/sphinx_highlight.js"></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="Huggingface" href="../huggingface/index.html" />
|
|
<link rel="prev" title="Follow the code style" href="code-style.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" />
|
|
<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="../installation/index.html">Installation</a></li>
|
|
<li class="toctree-l1"><a class="reference internal" href="../model-export/index.html">Model export</a></li>
|
|
<li class="toctree-l1"><a class="reference internal" href="../recipes/index.html">Recipes</a></li>
|
|
<li class="toctree-l1 current"><a class="reference internal" href="index.html">Contributing</a><ul class="current">
|
|
<li class="toctree-l2"><a class="reference internal" href="doc.html">Contributing to Documentation</a></li>
|
|
<li class="toctree-l2"><a class="reference internal" href="code-style.html">Follow the code style</a></li>
|
|
<li class="toctree-l2 current"><a class="current reference internal" href="#">How to create a recipe</a><ul>
|
|
<li class="toctree-l3"><a class="reference internal" href="#data-preparation">Data Preparation</a></li>
|
|
<li class="toctree-l3"><a class="reference internal" href="#training">Training</a></li>
|
|
<li class="toctree-l3"><a class="reference internal" href="#decoding">Decoding</a></li>
|
|
<li class="toctree-l3"><a class="reference internal" href="#pre-trained-model">Pre-trained model</a></li>
|
|
</ul>
|
|
</li>
|
|
</ul>
|
|
</li>
|
|
<li class="toctree-l1"><a class="reference internal" href="../huggingface/index.html">Huggingface</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"></a></li>
|
|
<li class="breadcrumb-item"><a href="index.html">Contributing</a></li>
|
|
<li class="breadcrumb-item active">How to create a recipe</li>
|
|
<li class="wy-breadcrumbs-aside">
|
|
<a href="https://github.com/k2-fsa/icefall/blob/master/docs/source/contributing/how-to-create-a-recipe.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="how-to-create-a-recipe">
|
|
<h1>How to create a recipe<a class="headerlink" href="#how-to-create-a-recipe" title="Permalink to this heading"></a></h1>
|
|
<div class="admonition hint">
|
|
<p class="admonition-title">Hint</p>
|
|
<p>Please read <a class="reference internal" href="code-style.html#follow-the-code-style"><span class="std std-ref">Follow the code style</span></a> to adjust your code sytle.</p>
|
|
</div>
|
|
<div class="admonition caution">
|
|
<p class="admonition-title">Caution</p>
|
|
<p><code class="docutils literal notranslate"><span class="pre">icefall</span></code> is designed to be as Pythonic as possible. Please use
|
|
Python in your recipe if possible.</p>
|
|
</div>
|
|
<section id="data-preparation">
|
|
<h2>Data Preparation<a class="headerlink" href="#data-preparation" title="Permalink to this heading"></a></h2>
|
|
<p>We recommend you to prepare your training/test/validate dataset
|
|
with <a class="reference external" href="https://github.com/lhotse-speech/lhotse">lhotse</a>.</p>
|
|
<p>Please refer to <a class="reference external" href="https://lhotse.readthedocs.io/en/latest/index.html">https://lhotse.readthedocs.io/en/latest/index.html</a>
|
|
for how to create a recipe in <code class="docutils literal notranslate"><span class="pre">lhotse</span></code>.</p>
|
|
<div class="admonition hint">
|
|
<p class="admonition-title">Hint</p>
|
|
<p>The <code class="docutils literal notranslate"><span class="pre">yesno</span></code> recipe in <code class="docutils literal notranslate"><span class="pre">lhotse</span></code> is a very good example.</p>
|
|
<p>Please refer to <a class="reference external" href="https://github.com/lhotse-speech/lhotse/pull/380">https://github.com/lhotse-speech/lhotse/pull/380</a>,
|
|
which shows how to add a new recipe to <code class="docutils literal notranslate"><span class="pre">lhotse</span></code>.</p>
|
|
</div>
|
|
<p>Suppose you would like to add a recipe for a dataset named <code class="docutils literal notranslate"><span class="pre">foo</span></code>.
|
|
You can do the following:</p>
|
|
<div class="highlight-default notranslate"><div class="highlight"><pre><span></span>$ cd egs
|
|
$ mkdir -p foo/ASR
|
|
$ cd foo/ASR
|
|
$ touch prepare.sh
|
|
$ chmod +x prepare.sh
|
|
</pre></div>
|
|
</div>
|
|
<p>If your dataset is very simple, please follow
|
|
<a class="reference external" href="https://github.com/k2-fsa/icefall/blob/master/egs/yesno/ASR/prepare.sh">egs/yesno/ASR/prepare.sh</a>
|
|
to write your own <code class="docutils literal notranslate"><span class="pre">prepare.sh</span></code>.
|
|
Otherwise, please refer to
|
|
<a class="reference external" href="https://github.com/k2-fsa/icefall/blob/master/egs/yesno/ASR/prepare.sh">egs/librispeech/ASR/prepare.sh</a>
|
|
to prepare your data.</p>
|
|
</section>
|
|
<section id="training">
|
|
<h2>Training<a class="headerlink" href="#training" title="Permalink to this heading"></a></h2>
|
|
<p>Assume you have a fancy model, called <code class="docutils literal notranslate"><span class="pre">bar</span></code> for the <code class="docutils literal notranslate"><span class="pre">foo</span></code> recipe, you can
|
|
organize your files in the following way:</p>
|
|
<div class="highlight-default notranslate"><div class="highlight"><pre><span></span>$ cd egs/foo/ASR
|
|
$ mkdir bar
|
|
$ cd bar
|
|
$ touch README.md model.py train.py decode.py asr_datamodule.py pretrained.py
|
|
</pre></div>
|
|
</div>
|
|
<p>For instance , the <code class="docutils literal notranslate"><span class="pre">yesno</span></code> recipe has a <code class="docutils literal notranslate"><span class="pre">tdnn</span></code> model and its directory structure
|
|
looks like the following:</p>
|
|
<div class="highlight-bash notranslate"><div class="highlight"><pre><span></span>egs/yesno/ASR/tdnn/
|
|
<span class="p">|</span>-- README.md
|
|
<span class="p">|</span>-- asr_datamodule.py
|
|
<span class="p">|</span>-- decode.py
|
|
<span class="p">|</span>-- model.py
|
|
<span class="p">|</span>-- pretrained.py
|
|
<span class="sb">`</span>-- train.py
|
|
</pre></div>
|
|
</div>
|
|
<p><strong>File description</strong>:</p>
|
|
<blockquote>
|
|
<div><ul>
|
|
<li><p><code class="docutils literal notranslate"><span class="pre">README.md</span></code></p>
|
|
<p>It contains information of this recipe, e.g., how to run it, what the WER is, etc.</p>
|
|
</li>
|
|
<li><p><code class="docutils literal notranslate"><span class="pre">asr_datamodule.py</span></code></p>
|
|
<p>It provides code to create PyTorch dataloaders with train/test/validation dataset.</p>
|
|
</li>
|
|
<li><p><code class="docutils literal notranslate"><span class="pre">decode.py</span></code></p>
|
|
<p>It takes as inputs the checkpoints saved during the training stage to decode the test
|
|
dataset(s).</p>
|
|
</li>
|
|
<li><p><code class="docutils literal notranslate"><span class="pre">model.py</span></code></p>
|
|
<p>It contains the definition of your fancy neural network model.</p>
|
|
</li>
|
|
<li><p><code class="docutils literal notranslate"><span class="pre">pretrained.py</span></code></p>
|
|
<p>We can use this script to do inference with a pre-trained model.</p>
|
|
</li>
|
|
<li><p><code class="docutils literal notranslate"><span class="pre">train.py</span></code></p>
|
|
<p>It contains training code.</p>
|
|
</li>
|
|
</ul>
|
|
</div></blockquote>
|
|
<div class="admonition hint">
|
|
<p class="admonition-title">Hint</p>
|
|
<p>Please take a look at</p>
|
|
<blockquote>
|
|
<div><ul class="simple">
|
|
<li><p><a class="reference external" href="https://github.com/k2-fsa/icefall/tree/master/egs/yesno/ASR/tdnn">egs/yesno/tdnn</a></p></li>
|
|
<li><p><a class="reference external" href="https://github.com/k2-fsa/icefall/tree/master/egs/librispeech/ASR/tdnn_lstm_ctc">egs/librispeech/tdnn_lstm_ctc</a></p></li>
|
|
<li><p><a class="reference external" href="https://github.com/k2-fsa/icefall/tree/master/egs/librispeech/ASR/conformer_ctc">egs/librispeech/conformer_ctc</a></p></li>
|
|
</ul>
|
|
</div></blockquote>
|
|
<p>to get a feel what the resulting files look like.</p>
|
|
</div>
|
|
<div class="admonition note">
|
|
<p class="admonition-title">Note</p>
|
|
<p>Every model in a recipe is kept to be as self-contained as possible.
|
|
We tolerate duplicate code among different recipes.</p>
|
|
</div>
|
|
<p>The training stage should be invocable by:</p>
|
|
<blockquote>
|
|
<div><div class="highlight-default notranslate"><div class="highlight"><pre><span></span>$ cd egs/foo/ASR
|
|
$ ./bar/train.py
|
|
$ ./bar/train.py --help
|
|
</pre></div>
|
|
</div>
|
|
</div></blockquote>
|
|
</section>
|
|
<section id="decoding">
|
|
<h2>Decoding<a class="headerlink" href="#decoding" title="Permalink to this heading"></a></h2>
|
|
<p>Please refer to</p>
|
|
<blockquote>
|
|
<div><ul>
|
|
<li><p><a class="reference external" href="https://github.com/k2-fsa/icefall/blob/master/egs/librispeech/ASR/conformer_ctc/decode.py">https://github.com/k2-fsa/icefall/blob/master/egs/librispeech/ASR/conformer_ctc/decode.py</a></p>
|
|
<p>If your model is transformer/conformer based.</p>
|
|
</li>
|
|
<li><p><a class="reference external" href="https://github.com/k2-fsa/icefall/blob/master/egs/librispeech/ASR/tdnn_lstm_ctc/decode.py">https://github.com/k2-fsa/icefall/blob/master/egs/librispeech/ASR/tdnn_lstm_ctc/decode.py</a></p>
|
|
<p>If your model is TDNN/LSTM based, i.e., there is no attention decoder.</p>
|
|
</li>
|
|
<li><p><a class="reference external" href="https://github.com/k2-fsa/icefall/blob/master/egs/yesno/ASR/tdnn/decode.py">https://github.com/k2-fsa/icefall/blob/master/egs/yesno/ASR/tdnn/decode.py</a></p>
|
|
<p>If there is no LM rescoring.</p>
|
|
</li>
|
|
</ul>
|
|
</div></blockquote>
|
|
<p>The decoding stage should be invocable by:</p>
|
|
<blockquote>
|
|
<div><div class="highlight-default notranslate"><div class="highlight"><pre><span></span>$ cd egs/foo/ASR
|
|
$ ./bar/decode.py
|
|
$ ./bar/decode.py --help
|
|
</pre></div>
|
|
</div>
|
|
</div></blockquote>
|
|
</section>
|
|
<section id="pre-trained-model">
|
|
<h2>Pre-trained model<a class="headerlink" href="#pre-trained-model" title="Permalink to this heading"></a></h2>
|
|
<p>Please demonstrate how to use your model for inference in <code class="docutils literal notranslate"><span class="pre">egs/foo/ASR/bar/pretrained.py</span></code>.
|
|
If possible, please consider creating a Colab notebook to show that.</p>
|
|
</section>
|
|
</section>
|
|
|
|
|
|
</div>
|
|
</div>
|
|
<footer><div class="rst-footer-buttons" role="navigation" aria-label="Footer">
|
|
<a href="code-style.html" class="btn btn-neutral float-left" title="Follow the code style" accesskey="p" rel="prev"><span class="fa fa-arrow-circle-left" aria-hidden="true"></span> Previous</a>
|
|
<a href="../huggingface/index.html" class="btn btn-neutral float-right" title="Huggingface" 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> |