mirror of
https://github.com/k2-fsa/icefall.git
synced 2025-08-09 18:12:19 +00:00
644 lines
49 KiB
HTML
644 lines
49 KiB
HTML
<!DOCTYPE html>
|
||
<html class="writer-html5" lang="en" >
|
||
<head>
|
||
<meta charset="utf-8" /><meta name="generator" content="Docutils 0.18.1: http://docutils.sourceforge.net/" />
|
||
|
||
<meta name="viewport" content="width=device-width, initial-scale=1.0" />
|
||
<title>LSTM Transducer — 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 src="../../../_static/jquery.js"></script>
|
||
<script src="../../../_static/_sphinx_javascript_frameworks_compat.js"></script>
|
||
<script data-url_root="../../../" id="documentation_options" src="../../../_static/documentation_options.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="Zipformer Transducer" href="zipformer_transducer.html" />
|
||
<link rel="prev" title="Pruned transducer statelessX" href="pruned_transducer_stateless.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>
|
||
<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>
|
||
</ul>
|
||
<ul class="current">
|
||
<li class="toctree-l1 current"><a class="reference internal" href="../../index.html">Recipes</a><ul class="current">
|
||
<li class="toctree-l2"><a class="reference internal" href="../../Non-streaming-ASR/index.html">Non Streaming ASR</a></li>
|
||
<li class="toctree-l2 current"><a class="reference internal" href="../index.html">Streaming ASR</a><ul class="current">
|
||
<li class="toctree-l3"><a class="reference internal" href="../introduction.html">Introduction</a></li>
|
||
<li class="toctree-l3 current"><a class="reference internal" href="index.html">LibriSpeech</a><ul class="current">
|
||
<li class="toctree-l4"><a class="reference internal" href="pruned_transducer_stateless.html">Pruned transducer statelessX</a></li>
|
||
<li class="toctree-l4 current"><a class="current reference internal" href="#">LSTM Transducer</a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="zipformer_transducer.html">Zipformer Transducer</a></li>
|
||
</ul>
|
||
</li>
|
||
</ul>
|
||
</li>
|
||
</ul>
|
||
</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"><a href="../../index.html">Recipes</a></li>
|
||
<li class="breadcrumb-item"><a href="../index.html">Streaming ASR</a></li>
|
||
<li class="breadcrumb-item"><a href="index.html">LibriSpeech</a></li>
|
||
<li class="breadcrumb-item active">LSTM Transducer</li>
|
||
<li class="wy-breadcrumbs-aside">
|
||
<a href="https://github.com/k2-fsa/icefall/blob/master/docs/source/recipes/Streaming-ASR/librispeech/lstm_pruned_stateless_transducer.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="lstm-transducer">
|
||
<h1>LSTM Transducer<a class="headerlink" href="#lstm-transducer" title="Permalink to this heading"></a></h1>
|
||
<div class="admonition hint">
|
||
<p class="admonition-title">Hint</p>
|
||
<p>Please scroll down to the bottom of this page to find download links
|
||
for pretrained models if you don’t want to train a model from scratch.</p>
|
||
</div>
|
||
<p>This tutorial shows you how to train an LSTM transducer model
|
||
with the <a class="reference external" href="https://www.openslr.org/12">LibriSpeech</a> dataset.</p>
|
||
<p>We use pruned RNN-T to compute the loss.</p>
|
||
<div class="admonition note">
|
||
<p class="admonition-title">Note</p>
|
||
<p>You can find the paper about pruned RNN-T at the following address:</p>
|
||
<p><a class="reference external" href="https://arxiv.org/abs/2206.13236">https://arxiv.org/abs/2206.13236</a></p>
|
||
</div>
|
||
<p>The transducer model consists of 3 parts:</p>
|
||
<blockquote>
|
||
<div><ul class="simple">
|
||
<li><p>Encoder, a.k.a, the transcription network. We use an LSTM model</p></li>
|
||
<li><p>Decoder, a.k.a, the prediction network. We use a stateless model consisting of
|
||
<code class="docutils literal notranslate"><span class="pre">nn.Embedding</span></code> and <code class="docutils literal notranslate"><span class="pre">nn.Conv1d</span></code></p></li>
|
||
<li><p>Joiner, a.k.a, the joint network.</p></li>
|
||
</ul>
|
||
</div></blockquote>
|
||
<div class="admonition caution">
|
||
<p class="admonition-title">Caution</p>
|
||
<p>Contrary to the conventional RNN-T models, we use a stateless decoder.
|
||
That is, it has no recurrent connections.</p>
|
||
</div>
|
||
<div class="admonition hint">
|
||
<p class="admonition-title">Hint</p>
|
||
<p>Since the encoder model is an LSTM, not Transformer/Conformer, the
|
||
resulting model is suitable for streaming/online ASR.</p>
|
||
</div>
|
||
<section id="which-model-to-use">
|
||
<h2>Which model to use<a class="headerlink" href="#which-model-to-use" title="Permalink to this heading"></a></h2>
|
||
<p>Currently, there are two folders about LSTM stateless transducer training:</p>
|
||
<blockquote>
|
||
<div><ul>
|
||
<li><p><code class="docutils literal notranslate"><span class="pre">(1)</span></code> <a class="reference external" href="https://github.com/k2-fsa/icefall/tree/master/egs/librispeech/ASR/lstm_transducer_stateless">https://github.com/k2-fsa/icefall/tree/master/egs/librispeech/ASR/lstm_transducer_stateless</a></p>
|
||
<p>This recipe uses only LibriSpeech during training.</p>
|
||
</li>
|
||
<li><p><code class="docutils literal notranslate"><span class="pre">(2)</span></code> <a class="reference external" href="https://github.com/k2-fsa/icefall/tree/master/egs/librispeech/ASR/lstm_transducer_stateless2">https://github.com/k2-fsa/icefall/tree/master/egs/librispeech/ASR/lstm_transducer_stateless2</a></p>
|
||
<p>This recipe uses GigaSpeech + LibriSpeech during training.</p>
|
||
</li>
|
||
</ul>
|
||
</div></blockquote>
|
||
<p><code class="docutils literal notranslate"><span class="pre">(1)</span></code> and <code class="docutils literal notranslate"><span class="pre">(2)</span></code> use the same model architecture. The only difference is that <code class="docutils literal notranslate"><span class="pre">(2)</span></code> supports
|
||
multi-dataset. Since <code class="docutils literal notranslate"><span class="pre">(2)</span></code> uses more data, it has a lower WER than <code class="docutils literal notranslate"><span class="pre">(1)</span></code> but it needs
|
||
more training time.</p>
|
||
<p>We use <code class="docutils literal notranslate"><span class="pre">lstm_transducer_stateless2</span></code> as an example below.</p>
|
||
<div class="admonition note">
|
||
<p class="admonition-title">Note</p>
|
||
<p>You need to download the <a class="reference external" href="https://github.com/SpeechColab/GigaSpeech">GigaSpeech</a> dataset
|
||
to run <code class="docutils literal notranslate"><span class="pre">(2)</span></code>. If you have only <code class="docutils literal notranslate"><span class="pre">LibriSpeech</span></code> dataset available, feel free to use <code class="docutils literal notranslate"><span class="pre">(1)</span></code>.</p>
|
||
</div>
|
||
</section>
|
||
<section id="data-preparation">
|
||
<h2>Data preparation<a class="headerlink" href="#data-preparation" title="Permalink to this heading"></a></h2>
|
||
<div class="highlight-bash notranslate"><div class="highlight"><pre><span></span>$<span class="w"> </span><span class="nb">cd</span><span class="w"> </span>egs/librispeech/ASR
|
||
$<span class="w"> </span>./prepare.sh
|
||
|
||
<span class="c1"># If you use (1), you can **skip** the following command</span>
|
||
$<span class="w"> </span>./prepare_giga_speech.sh
|
||
</pre></div>
|
||
</div>
|
||
<p>The script <code class="docutils literal notranslate"><span class="pre">./prepare.sh</span></code> handles the data preparation for you, <strong>automagically</strong>.
|
||
All you need to do is to run it.</p>
|
||
<div class="admonition note">
|
||
<p class="admonition-title">Note</p>
|
||
<p>We encourage you to read <code class="docutils literal notranslate"><span class="pre">./prepare.sh</span></code>.</p>
|
||
</div>
|
||
<p>The data preparation contains several stages. You can use the following two
|
||
options:</p>
|
||
<blockquote>
|
||
<div><ul class="simple">
|
||
<li><p><code class="docutils literal notranslate"><span class="pre">--stage</span></code></p></li>
|
||
<li><p><code class="docutils literal notranslate"><span class="pre">--stop-stage</span></code></p></li>
|
||
</ul>
|
||
</div></blockquote>
|
||
<p>to control which stage(s) should be run. By default, all stages are executed.</p>
|
||
<p>For example,</p>
|
||
<div class="highlight-bash notranslate"><div class="highlight"><pre><span></span>$<span class="w"> </span><span class="nb">cd</span><span class="w"> </span>egs/librispeech/ASR
|
||
$<span class="w"> </span>./prepare.sh<span class="w"> </span>--stage<span class="w"> </span><span class="m">0</span><span class="w"> </span>--stop-stage<span class="w"> </span><span class="m">0</span>
|
||
</pre></div>
|
||
</div>
|
||
<p>means to run only stage 0.</p>
|
||
<p>To run stage 2 to stage 5, use:</p>
|
||
<div class="highlight-bash notranslate"><div class="highlight"><pre><span></span>$<span class="w"> </span>./prepare.sh<span class="w"> </span>--stage<span class="w"> </span><span class="m">2</span><span class="w"> </span>--stop-stage<span class="w"> </span><span class="m">5</span>
|
||
</pre></div>
|
||
</div>
|
||
<div class="admonition hint">
|
||
<p class="admonition-title">Hint</p>
|
||
<p>If you have pre-downloaded the <a class="reference external" href="https://www.openslr.org/12">LibriSpeech</a>
|
||
dataset and the <a class="reference external" href="http://www.openslr.org/17/">musan</a> dataset, say,
|
||
they are saved in <code class="docutils literal notranslate"><span class="pre">/tmp/LibriSpeech</span></code> and <code class="docutils literal notranslate"><span class="pre">/tmp/musan</span></code>, you can modify
|
||
the <code class="docutils literal notranslate"><span class="pre">dl_dir</span></code> variable in <code class="docutils literal notranslate"><span class="pre">./prepare.sh</span></code> to point to <code class="docutils literal notranslate"><span class="pre">/tmp</span></code> so that
|
||
<code class="docutils literal notranslate"><span class="pre">./prepare.sh</span></code> won’t re-download them.</p>
|
||
</div>
|
||
<div class="admonition note">
|
||
<p class="admonition-title">Note</p>
|
||
<p>All generated files by <code class="docutils literal notranslate"><span class="pre">./prepare.sh</span></code>, e.g., features, lexicon, etc,
|
||
are saved in <code class="docutils literal notranslate"><span class="pre">./data</span></code> directory.</p>
|
||
</div>
|
||
<p>We provide the following YouTube video showing how to run <code class="docutils literal notranslate"><span class="pre">./prepare.sh</span></code>.</p>
|
||
<div class="admonition note">
|
||
<p class="admonition-title">Note</p>
|
||
<p>To get the latest news of <a class="reference external" href="https://github.com/k2-fsa">next-gen Kaldi</a>, please subscribe
|
||
the following YouTube channel by <a class="reference external" href="https://www.youtube.com/channel/UC_VaumpkmINz1pNkFXAN9mw">Nadira Povey</a>:</p>
|
||
<blockquote>
|
||
<div><p><a class="reference external" href="https://www.youtube.com/channel/UC_VaumpkmINz1pNkFXAN9mw">https://www.youtube.com/channel/UC_VaumpkmINz1pNkFXAN9mw</a></p>
|
||
</div></blockquote>
|
||
</div>
|
||
<div class="video_wrapper" style="">
|
||
<iframe allowfullscreen="true" src="https://www.youtube.com/embed/ofEIoJL-mGM" style="border: 0; height: 345px; width: 560px">
|
||
</iframe></div></section>
|
||
<section id="training">
|
||
<h2>Training<a class="headerlink" href="#training" title="Permalink to this heading"></a></h2>
|
||
<section id="configurable-options">
|
||
<h3>Configurable options<a class="headerlink" href="#configurable-options" title="Permalink to this heading"></a></h3>
|
||
<div class="highlight-bash notranslate"><div class="highlight"><pre><span></span>$<span class="w"> </span><span class="nb">cd</span><span class="w"> </span>egs/librispeech/ASR
|
||
$<span class="w"> </span>./lstm_transducer_stateless2/train.py<span class="w"> </span>--help
|
||
</pre></div>
|
||
</div>
|
||
<p>shows you the training options that can be passed from the commandline.
|
||
The following options are used quite often:</p>
|
||
<blockquote>
|
||
<div><ul>
|
||
<li><p><code class="docutils literal notranslate"><span class="pre">--full-libri</span></code></p>
|
||
<p>If it’s True, the training part uses all the training data, i.e.,
|
||
960 hours. Otherwise, the training part uses only the subset
|
||
<code class="docutils literal notranslate"><span class="pre">train-clean-100</span></code>, which has 100 hours of training data.</p>
|
||
<div class="admonition caution">
|
||
<p class="admonition-title">Caution</p>
|
||
<p>The training set is perturbed by speed with two factors: 0.9 and 1.1.
|
||
If <code class="docutils literal notranslate"><span class="pre">--full-libri</span></code> is True, each epoch actually processes
|
||
<code class="docutils literal notranslate"><span class="pre">3x960</span> <span class="pre">==</span> <span class="pre">2880</span></code> hours of data.</p>
|
||
</div>
|
||
</li>
|
||
<li><p><code class="docutils literal notranslate"><span class="pre">--num-epochs</span></code></p>
|
||
<p>It is the number of epochs to train. For instance,
|
||
<code class="docutils literal notranslate"><span class="pre">./lstm_transducer_stateless2/train.py</span> <span class="pre">--num-epochs</span> <span class="pre">30</span></code> trains for 30 epochs
|
||
and generates <code class="docutils literal notranslate"><span class="pre">epoch-1.pt</span></code>, <code class="docutils literal notranslate"><span class="pre">epoch-2.pt</span></code>, …, <code class="docutils literal notranslate"><span class="pre">epoch-30.pt</span></code>
|
||
in the folder <code class="docutils literal notranslate"><span class="pre">./lstm_transducer_stateless2/exp</span></code>.</p>
|
||
</li>
|
||
<li><p><code class="docutils literal notranslate"><span class="pre">--start-epoch</span></code></p>
|
||
<p>It’s used to resume training.
|
||
<code class="docutils literal notranslate"><span class="pre">./lstm_transducer_stateless2/train.py</span> <span class="pre">--start-epoch</span> <span class="pre">10</span></code> loads the
|
||
checkpoint <code class="docutils literal notranslate"><span class="pre">./lstm_transducer_stateless2/exp/epoch-9.pt</span></code> and starts
|
||
training from epoch 10, based on the state from epoch 9.</p>
|
||
</li>
|
||
<li><p><code class="docutils literal notranslate"><span class="pre">--world-size</span></code></p>
|
||
<p>It is used for multi-GPU single-machine DDP training.</p>
|
||
<blockquote>
|
||
<div><ul class="simple">
|
||
<li><ol class="loweralpha simple">
|
||
<li><p>If it is 1, then no DDP training is used.</p></li>
|
||
</ol>
|
||
</li>
|
||
<li><ol class="loweralpha simple" start="2">
|
||
<li><p>If it is 2, then GPU 0 and GPU 1 are used for DDP training.</p></li>
|
||
</ol>
|
||
</li>
|
||
</ul>
|
||
</div></blockquote>
|
||
<p>The following shows some use cases with it.</p>
|
||
<blockquote>
|
||
<div><p><strong>Use case 1</strong>: You have 4 GPUs, but you only want to use GPU 0 and
|
||
GPU 2 for training. You can do the following:</p>
|
||
<blockquote>
|
||
<div><div class="highlight-bash notranslate"><div class="highlight"><pre><span></span>$<span class="w"> </span><span class="nb">cd</span><span class="w"> </span>egs/librispeech/ASR
|
||
$<span class="w"> </span><span class="nb">export</span><span class="w"> </span><span class="nv">CUDA_VISIBLE_DEVICES</span><span class="o">=</span><span class="s2">"0,2"</span>
|
||
$<span class="w"> </span>./lstm_transducer_stateless2/train.py<span class="w"> </span>--world-size<span class="w"> </span><span class="m">2</span>
|
||
</pre></div>
|
||
</div>
|
||
</div></blockquote>
|
||
<p><strong>Use case 2</strong>: You have 4 GPUs and you want to use all of them
|
||
for training. You can do the following:</p>
|
||
<blockquote>
|
||
<div><div class="highlight-bash notranslate"><div class="highlight"><pre><span></span>$<span class="w"> </span><span class="nb">cd</span><span class="w"> </span>egs/librispeech/ASR
|
||
$<span class="w"> </span>./lstm_transducer_stateless2/train.py<span class="w"> </span>--world-size<span class="w"> </span><span class="m">4</span>
|
||
</pre></div>
|
||
</div>
|
||
</div></blockquote>
|
||
<p><strong>Use case 3</strong>: You have 4 GPUs but you only want to use GPU 3
|
||
for training. You can do the following:</p>
|
||
<blockquote>
|
||
<div><div class="highlight-bash notranslate"><div class="highlight"><pre><span></span>$<span class="w"> </span><span class="nb">cd</span><span class="w"> </span>egs/librispeech/ASR
|
||
$<span class="w"> </span><span class="nb">export</span><span class="w"> </span><span class="nv">CUDA_VISIBLE_DEVICES</span><span class="o">=</span><span class="s2">"3"</span>
|
||
$<span class="w"> </span>./lstm_transducer_stateless2/train.py<span class="w"> </span>--world-size<span class="w"> </span><span class="m">1</span>
|
||
</pre></div>
|
||
</div>
|
||
</div></blockquote>
|
||
</div></blockquote>
|
||
<div class="admonition caution">
|
||
<p class="admonition-title">Caution</p>
|
||
<p>Only multi-GPU single-machine DDP training is implemented at present.
|
||
Multi-GPU multi-machine DDP training will be added later.</p>
|
||
</div>
|
||
</li>
|
||
<li><p><code class="docutils literal notranslate"><span class="pre">--max-duration</span></code></p>
|
||
<p>It specifies the number of seconds over all utterances in a
|
||
batch, before <strong>padding</strong>.
|
||
If you encounter CUDA OOM, please reduce it.</p>
|
||
<div class="admonition hint">
|
||
<p class="admonition-title">Hint</p>
|
||
<p>Due to padding, the number of seconds of all utterances in a
|
||
batch will usually be larger than <code class="docutils literal notranslate"><span class="pre">--max-duration</span></code>.</p>
|
||
<p>A larger value for <code class="docutils literal notranslate"><span class="pre">--max-duration</span></code> may cause OOM during training,
|
||
while a smaller value may increase the training time. You have to
|
||
tune it.</p>
|
||
</div>
|
||
</li>
|
||
<li><p><code class="docutils literal notranslate"><span class="pre">--giga-prob</span></code></p>
|
||
<p>The probability to select a batch from the <code class="docutils literal notranslate"><span class="pre">GigaSpeech</span></code> dataset.
|
||
Note: It is available only for <code class="docutils literal notranslate"><span class="pre">(2)</span></code>.</p>
|
||
</li>
|
||
</ul>
|
||
</div></blockquote>
|
||
</section>
|
||
<section id="pre-configured-options">
|
||
<h3>Pre-configured options<a class="headerlink" href="#pre-configured-options" title="Permalink to this heading"></a></h3>
|
||
<p>There are some training options, e.g., weight decay,
|
||
number of warmup steps, results dir, etc,
|
||
that are not passed from the commandline.
|
||
They are pre-configured by the function <code class="docutils literal notranslate"><span class="pre">get_params()</span></code> in
|
||
<a class="reference external" href="https://github.com/k2-fsa/icefall/blob/master/egs/librispeech/ASR/lstm_transducer_stateless2/train.py">lstm_transducer_stateless2/train.py</a></p>
|
||
<p>You don’t need to change these pre-configured parameters. If you really need to change
|
||
them, please modify <code class="docutils literal notranslate"><span class="pre">./lstm_transducer_stateless2/train.py</span></code> directly.</p>
|
||
</section>
|
||
<section id="training-logs">
|
||
<h3>Training logs<a class="headerlink" href="#training-logs" title="Permalink to this heading"></a></h3>
|
||
<p>Training logs and checkpoints are saved in <code class="docutils literal notranslate"><span class="pre">lstm_transducer_stateless2/exp</span></code>.
|
||
You will find the following files in that directory:</p>
|
||
<blockquote>
|
||
<div><ul>
|
||
<li><p><code class="docutils literal notranslate"><span class="pre">epoch-1.pt</span></code>, <code class="docutils literal notranslate"><span class="pre">epoch-2.pt</span></code>, …</p>
|
||
<p>These are checkpoint files saved at the end of each epoch, containing model
|
||
<code class="docutils literal notranslate"><span class="pre">state_dict</span></code> and optimizer <code class="docutils literal notranslate"><span class="pre">state_dict</span></code>.
|
||
To resume training from some checkpoint, say <code class="docutils literal notranslate"><span class="pre">epoch-10.pt</span></code>, you can use:</p>
|
||
<blockquote>
|
||
<div><div class="highlight-bash notranslate"><div class="highlight"><pre><span></span>$<span class="w"> </span>./lstm_transducer_stateless2/train.py<span class="w"> </span>--start-epoch<span class="w"> </span><span class="m">11</span>
|
||
</pre></div>
|
||
</div>
|
||
</div></blockquote>
|
||
</li>
|
||
<li><p><code class="docutils literal notranslate"><span class="pre">checkpoint-436000.pt</span></code>, <code class="docutils literal notranslate"><span class="pre">checkpoint-438000.pt</span></code>, …</p>
|
||
<p>These are checkpoint files saved every <code class="docutils literal notranslate"><span class="pre">--save-every-n</span></code> batches,
|
||
containing model <code class="docutils literal notranslate"><span class="pre">state_dict</span></code> and optimizer <code class="docutils literal notranslate"><span class="pre">state_dict</span></code>.
|
||
To resume training from some checkpoint, say <code class="docutils literal notranslate"><span class="pre">checkpoint-436000</span></code>, you can use:</p>
|
||
<blockquote>
|
||
<div><div class="highlight-bash notranslate"><div class="highlight"><pre><span></span>$<span class="w"> </span>./lstm_transducer_stateless2/train.py<span class="w"> </span>--start-batch<span class="w"> </span><span class="m">436000</span>
|
||
</pre></div>
|
||
</div>
|
||
</div></blockquote>
|
||
</li>
|
||
<li><p><code class="docutils literal notranslate"><span class="pre">tensorboard/</span></code></p>
|
||
<p>This folder contains tensorBoard logs. Training loss, validation loss, learning
|
||
rate, etc, are recorded in these logs. You can visualize them by:</p>
|
||
<blockquote>
|
||
<div><div class="highlight-bash notranslate"><div class="highlight"><pre><span></span>$<span class="w"> </span><span class="nb">cd</span><span class="w"> </span>lstm_transducer_stateless2/exp/tensorboard
|
||
$<span class="w"> </span>tensorboard<span class="w"> </span>dev<span class="w"> </span>upload<span class="w"> </span>--logdir<span class="w"> </span>.<span class="w"> </span>--description<span class="w"> </span><span class="s2">"LSTM transducer training for LibriSpeech with icefall"</span>
|
||
</pre></div>
|
||
</div>
|
||
</div></blockquote>
|
||
<p>It will print something like below:</p>
|
||
<blockquote>
|
||
<div><div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="n">TensorFlow</span> <span class="n">installation</span> <span class="ow">not</span> <span class="n">found</span> <span class="o">-</span> <span class="n">running</span> <span class="k">with</span> <span class="n">reduced</span> <span class="n">feature</span> <span class="nb">set</span><span class="o">.</span>
|
||
<span class="n">Upload</span> <span class="n">started</span> <span class="ow">and</span> <span class="n">will</span> <span class="k">continue</span> <span class="n">reading</span> <span class="nb">any</span> <span class="n">new</span> <span class="n">data</span> <span class="k">as</span> <span class="n">it</span><span class="s1">'s added to the logdir.</span>
|
||
|
||
<span class="n">To</span> <span class="n">stop</span> <span class="n">uploading</span><span class="p">,</span> <span class="n">press</span> <span class="n">Ctrl</span><span class="o">-</span><span class="n">C</span><span class="o">.</span>
|
||
|
||
<span class="n">New</span> <span class="n">experiment</span> <span class="n">created</span><span class="o">.</span> <span class="n">View</span> <span class="n">your</span> <span class="n">TensorBoard</span> <span class="n">at</span><span class="p">:</span> <span class="n">https</span><span class="p">:</span><span class="o">//</span><span class="n">tensorboard</span><span class="o">.</span><span class="n">dev</span><span class="o">/</span><span class="n">experiment</span><span class="o">/</span><span class="n">cj2vtPiwQHKN9Q1tx6PTpg</span><span class="o">/</span>
|
||
|
||
<span class="p">[</span><span class="mi">2022</span><span class="o">-</span><span class="mi">09</span><span class="o">-</span><span class="mi">20</span><span class="n">T15</span><span class="p">:</span><span class="mi">50</span><span class="p">:</span><span class="mi">50</span><span class="p">]</span> <span class="n">Started</span> <span class="n">scanning</span> <span class="n">logdir</span><span class="o">.</span>
|
||
<span class="n">Uploading</span> <span class="mi">4468</span> <span class="n">scalars</span><span class="o">...</span>
|
||
<span class="p">[</span><span class="mi">2022</span><span class="o">-</span><span class="mi">09</span><span class="o">-</span><span class="mi">20</span><span class="n">T15</span><span class="p">:</span><span class="mi">53</span><span class="p">:</span><span class="mi">02</span><span class="p">]</span> <span class="n">Total</span> <span class="n">uploaded</span><span class="p">:</span> <span class="mi">210171</span> <span class="n">scalars</span><span class="p">,</span> <span class="mi">0</span> <span class="n">tensors</span><span class="p">,</span> <span class="mi">0</span> <span class="n">binary</span> <span class="n">objects</span>
|
||
<span class="n">Listening</span> <span class="k">for</span> <span class="n">new</span> <span class="n">data</span> <span class="ow">in</span> <span class="n">logdir</span><span class="o">...</span>
|
||
</pre></div>
|
||
</div>
|
||
</div></blockquote>
|
||
<p>Note there is a URL in the above output. Click it and you will see
|
||
the following screenshot:</p>
|
||
<blockquote>
|
||
<div><figure class="align-center" id="id6">
|
||
<a class="reference external image-reference" href="https://tensorboard.dev/experiment/lzGnETjwRxC3yghNMd4kPw/"><img alt="TensorBoard screenshot" src="../../../_images/librispeech-lstm-transducer-tensorboard-log.png" style="width: 600px;" /></a>
|
||
<figcaption>
|
||
<p><span class="caption-number">Fig. 10 </span><span class="caption-text">TensorBoard screenshot.</span><a class="headerlink" href="#id6" title="Permalink to this image"></a></p>
|
||
</figcaption>
|
||
</figure>
|
||
</div></blockquote>
|
||
</li>
|
||
</ul>
|
||
<div class="admonition hint">
|
||
<p class="admonition-title">Hint</p>
|
||
<p>If you don’t have access to google, you can use the following command
|
||
to view the tensorboard log locally:</p>
|
||
<blockquote>
|
||
<div><div class="highlight-bash notranslate"><div class="highlight"><pre><span></span><span class="nb">cd</span><span class="w"> </span>lstm_transducer_stateless2/exp/tensorboard
|
||
tensorboard<span class="w"> </span>--logdir<span class="w"> </span>.<span class="w"> </span>--port<span class="w"> </span><span class="m">6008</span>
|
||
</pre></div>
|
||
</div>
|
||
</div></blockquote>
|
||
<p>It will print the following message:</p>
|
||
<blockquote>
|
||
<div><div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="n">Serving</span> <span class="n">TensorBoard</span> <span class="n">on</span> <span class="n">localhost</span><span class="p">;</span> <span class="n">to</span> <span class="n">expose</span> <span class="n">to</span> <span class="n">the</span> <span class="n">network</span><span class="p">,</span> <span class="n">use</span> <span class="n">a</span> <span class="n">proxy</span> <span class="ow">or</span> <span class="k">pass</span> <span class="o">--</span><span class="n">bind_all</span>
|
||
<span class="n">TensorBoard</span> <span class="mf">2.8.0</span> <span class="n">at</span> <span class="n">http</span><span class="p">:</span><span class="o">//</span><span class="n">localhost</span><span class="p">:</span><span class="mi">6008</span><span class="o">/</span> <span class="p">(</span><span class="n">Press</span> <span class="n">CTRL</span><span class="o">+</span><span class="n">C</span> <span class="n">to</span> <span class="n">quit</span><span class="p">)</span>
|
||
</pre></div>
|
||
</div>
|
||
</div></blockquote>
|
||
<p>Now start your browser and go to <a class="reference external" href="http://localhost:6008">http://localhost:6008</a> to view the tensorboard
|
||
logs.</p>
|
||
</div>
|
||
<ul>
|
||
<li><p><code class="docutils literal notranslate"><span class="pre">log/log-train-xxxx</span></code></p>
|
||
<p>It is the detailed training log in text format, same as the one
|
||
you saw printed to the console during training.</p>
|
||
</li>
|
||
</ul>
|
||
</div></blockquote>
|
||
</section>
|
||
<section id="usage-example">
|
||
<h3>Usage example<a class="headerlink" href="#usage-example" title="Permalink to this heading"></a></h3>
|
||
<p>You can use the following command to start the training using 8 GPUs:</p>
|
||
<div class="highlight-bash notranslate"><div class="highlight"><pre><span></span><span class="nb">export</span><span class="w"> </span><span class="nv">CUDA_VISIBLE_DEVICES</span><span class="o">=</span><span class="s2">"0,1,2,3,4,5,6,7"</span>
|
||
./lstm_transducer_stateless2/train.py<span class="w"> </span><span class="se">\</span>
|
||
<span class="w"> </span>--world-size<span class="w"> </span><span class="m">8</span><span class="w"> </span><span class="se">\</span>
|
||
<span class="w"> </span>--num-epochs<span class="w"> </span><span class="m">35</span><span class="w"> </span><span class="se">\</span>
|
||
<span class="w"> </span>--start-epoch<span class="w"> </span><span class="m">1</span><span class="w"> </span><span class="se">\</span>
|
||
<span class="w"> </span>--full-libri<span class="w"> </span><span class="m">1</span><span class="w"> </span><span class="se">\</span>
|
||
<span class="w"> </span>--exp-dir<span class="w"> </span>lstm_transducer_stateless2/exp<span class="w"> </span><span class="se">\</span>
|
||
<span class="w"> </span>--max-duration<span class="w"> </span><span class="m">500</span><span class="w"> </span><span class="se">\</span>
|
||
<span class="w"> </span>--use-fp16<span class="w"> </span><span class="m">0</span><span class="w"> </span><span class="se">\</span>
|
||
<span class="w"> </span>--lr-epochs<span class="w"> </span><span class="m">10</span><span class="w"> </span><span class="se">\</span>
|
||
<span class="w"> </span>--num-workers<span class="w"> </span><span class="m">2</span><span class="w"> </span><span class="se">\</span>
|
||
<span class="w"> </span>--giga-prob<span class="w"> </span><span class="m">0</span>.9
|
||
</pre></div>
|
||
</div>
|
||
</section>
|
||
</section>
|
||
<section id="decoding">
|
||
<h2>Decoding<a class="headerlink" href="#decoding" title="Permalink to this heading"></a></h2>
|
||
<p>The decoding part uses checkpoints saved by the training part, so you have
|
||
to run the training part first.</p>
|
||
<div class="admonition hint">
|
||
<p class="admonition-title">Hint</p>
|
||
<p>There are two kinds of checkpoints:</p>
|
||
<blockquote>
|
||
<div><ul class="simple">
|
||
<li><p>(1) <code class="docutils literal notranslate"><span class="pre">epoch-1.pt</span></code>, <code class="docutils literal notranslate"><span class="pre">epoch-2.pt</span></code>, …, which are saved at the end
|
||
of each epoch. You can pass <code class="docutils literal notranslate"><span class="pre">--epoch</span></code> to
|
||
<code class="docutils literal notranslate"><span class="pre">lstm_transducer_stateless2/decode.py</span></code> to use them.</p></li>
|
||
<li><p>(2) <code class="docutils literal notranslate"><span class="pre">checkpoints-436000.pt</span></code>, <code class="docutils literal notranslate"><span class="pre">epoch-438000.pt</span></code>, …, which are saved
|
||
every <code class="docutils literal notranslate"><span class="pre">--save-every-n</span></code> batches. You can pass <code class="docutils literal notranslate"><span class="pre">--iter</span></code> to
|
||
<code class="docutils literal notranslate"><span class="pre">lstm_transducer_stateless2/decode.py</span></code> to use them.</p></li>
|
||
</ul>
|
||
<p>We suggest that you try both types of checkpoints and choose the one
|
||
that produces the lowest WERs.</p>
|
||
</div></blockquote>
|
||
</div>
|
||
<div class="highlight-bash notranslate"><div class="highlight"><pre><span></span>$<span class="w"> </span><span class="nb">cd</span><span class="w"> </span>egs/librispeech/ASR
|
||
$<span class="w"> </span>./lstm_transducer_stateless2/decode.py<span class="w"> </span>--help
|
||
</pre></div>
|
||
</div>
|
||
<p>shows the options for decoding.</p>
|
||
<p>The following shows two examples:</p>
|
||
<div class="highlight-bash notranslate"><div class="highlight"><pre><span></span><span class="k">for</span><span class="w"> </span>m<span class="w"> </span><span class="k">in</span><span class="w"> </span>greedy_search<span class="w"> </span>fast_beam_search<span class="w"> </span>modified_beam_search<span class="p">;</span><span class="w"> </span><span class="k">do</span>
|
||
<span class="w"> </span><span class="k">for</span><span class="w"> </span>epoch<span class="w"> </span><span class="k">in</span><span class="w"> </span><span class="m">17</span><span class="p">;</span><span class="w"> </span><span class="k">do</span>
|
||
<span class="w"> </span><span class="k">for</span><span class="w"> </span>avg<span class="w"> </span><span class="k">in</span><span class="w"> </span><span class="m">1</span><span class="w"> </span><span class="m">2</span><span class="p">;</span><span class="w"> </span><span class="k">do</span>
|
||
<span class="w"> </span>./lstm_transducer_stateless2/decode.py<span class="w"> </span><span class="se">\</span>
|
||
<span class="w"> </span>--epoch<span class="w"> </span><span class="nv">$epoch</span><span class="w"> </span><span class="se">\</span>
|
||
<span class="w"> </span>--avg<span class="w"> </span><span class="nv">$avg</span><span class="w"> </span><span class="se">\</span>
|
||
<span class="w"> </span>--exp-dir<span class="w"> </span>lstm_transducer_stateless2/exp<span class="w"> </span><span class="se">\</span>
|
||
<span class="w"> </span>--max-duration<span class="w"> </span><span class="m">600</span><span class="w"> </span><span class="se">\</span>
|
||
<span class="w"> </span>--num-encoder-layers<span class="w"> </span><span class="m">12</span><span class="w"> </span><span class="se">\</span>
|
||
<span class="w"> </span>--rnn-hidden-size<span class="w"> </span><span class="m">1024</span><span class="w"> </span><span class="se">\</span>
|
||
<span class="w"> </span>--decoding-method<span class="w"> </span><span class="nv">$m</span><span class="w"> </span><span class="se">\</span>
|
||
<span class="w"> </span>--use-averaged-model<span class="w"> </span>True<span class="w"> </span><span class="se">\</span>
|
||
<span class="w"> </span>--beam<span class="w"> </span><span class="m">4</span><span class="w"> </span><span class="se">\</span>
|
||
<span class="w"> </span>--max-contexts<span class="w"> </span><span class="m">4</span><span class="w"> </span><span class="se">\</span>
|
||
<span class="w"> </span>--max-states<span class="w"> </span><span class="m">8</span><span class="w"> </span><span class="se">\</span>
|
||
<span class="w"> </span>--beam-size<span class="w"> </span><span class="m">4</span>
|
||
<span class="w"> </span><span class="k">done</span>
|
||
<span class="w"> </span><span class="k">done</span>
|
||
<span class="k">done</span>
|
||
</pre></div>
|
||
</div>
|
||
<div class="highlight-bash notranslate"><div class="highlight"><pre><span></span><span class="k">for</span><span class="w"> </span>m<span class="w"> </span><span class="k">in</span><span class="w"> </span>greedy_search<span class="w"> </span>fast_beam_search<span class="w"> </span>modified_beam_search<span class="p">;</span><span class="w"> </span><span class="k">do</span>
|
||
<span class="w"> </span><span class="k">for</span><span class="w"> </span>iter<span class="w"> </span><span class="k">in</span><span class="w"> </span><span class="m">474000</span><span class="p">;</span><span class="w"> </span><span class="k">do</span>
|
||
<span class="w"> </span><span class="k">for</span><span class="w"> </span>avg<span class="w"> </span><span class="k">in</span><span class="w"> </span><span class="m">8</span><span class="w"> </span><span class="m">10</span><span class="w"> </span><span class="m">12</span><span class="w"> </span><span class="m">14</span><span class="w"> </span><span class="m">16</span><span class="w"> </span><span class="m">18</span><span class="p">;</span><span class="w"> </span><span class="k">do</span>
|
||
<span class="w"> </span>./lstm_transducer_stateless2/decode.py<span class="w"> </span><span class="se">\</span>
|
||
<span class="w"> </span>--iter<span class="w"> </span><span class="nv">$iter</span><span class="w"> </span><span class="se">\</span>
|
||
<span class="w"> </span>--avg<span class="w"> </span><span class="nv">$avg</span><span class="w"> </span><span class="se">\</span>
|
||
<span class="w"> </span>--exp-dir<span class="w"> </span>lstm_transducer_stateless2/exp<span class="w"> </span><span class="se">\</span>
|
||
<span class="w"> </span>--max-duration<span class="w"> </span><span class="m">600</span><span class="w"> </span><span class="se">\</span>
|
||
<span class="w"> </span>--num-encoder-layers<span class="w"> </span><span class="m">12</span><span class="w"> </span><span class="se">\</span>
|
||
<span class="w"> </span>--rnn-hidden-size<span class="w"> </span><span class="m">1024</span><span class="w"> </span><span class="se">\</span>
|
||
<span class="w"> </span>--decoding-method<span class="w"> </span><span class="nv">$m</span><span class="w"> </span><span class="se">\</span>
|
||
<span class="w"> </span>--use-averaged-model<span class="w"> </span>True<span class="w"> </span><span class="se">\</span>
|
||
<span class="w"> </span>--beam<span class="w"> </span><span class="m">4</span><span class="w"> </span><span class="se">\</span>
|
||
<span class="w"> </span>--max-contexts<span class="w"> </span><span class="m">4</span><span class="w"> </span><span class="se">\</span>
|
||
<span class="w"> </span>--max-states<span class="w"> </span><span class="m">8</span><span class="w"> </span><span class="se">\</span>
|
||
<span class="w"> </span>--beam-size<span class="w"> </span><span class="m">4</span>
|
||
<span class="w"> </span><span class="k">done</span>
|
||
<span class="w"> </span><span class="k">done</span>
|
||
<span class="k">done</span>
|
||
</pre></div>
|
||
</div>
|
||
</section>
|
||
<section id="export-models">
|
||
<h2>Export models<a class="headerlink" href="#export-models" title="Permalink to this heading"></a></h2>
|
||
<p><a class="reference external" href="https://github.com/k2-fsa/icefall/blob/master/egs/librispeech/ASR/lstm_transducer_stateless2/export.py">lstm_transducer_stateless2/export.py</a> supports exporting checkpoints from <code class="docutils literal notranslate"><span class="pre">lstm_transducer_stateless2/exp</span></code> in the following ways.</p>
|
||
<section id="export-model-state-dict">
|
||
<h3>Export <code class="docutils literal notranslate"><span class="pre">model.state_dict()</span></code><a class="headerlink" href="#export-model-state-dict" title="Permalink to this heading"></a></h3>
|
||
<p>Checkpoints saved by <code class="docutils literal notranslate"><span class="pre">lstm_transducer_stateless2/train.py</span></code> also include
|
||
<code class="docutils literal notranslate"><span class="pre">optimizer.state_dict()</span></code>. It is useful for resuming training. But after training,
|
||
we are interested only in <code class="docutils literal notranslate"><span class="pre">model.state_dict()</span></code>. You can use the following
|
||
command to extract <code class="docutils literal notranslate"><span class="pre">model.state_dict()</span></code>.</p>
|
||
<div class="highlight-bash notranslate"><div class="highlight"><pre><span></span><span class="c1"># Assume that --iter 468000 --avg 16 produces the smallest WER</span>
|
||
<span class="c1"># (You can get such information after running ./lstm_transducer_stateless2/decode.py)</span>
|
||
|
||
<span class="nv">iter</span><span class="o">=</span><span class="m">468000</span>
|
||
<span class="nv">avg</span><span class="o">=</span><span class="m">16</span>
|
||
|
||
./lstm_transducer_stateless2/export.py<span class="w"> </span><span class="se">\</span>
|
||
<span class="w"> </span>--exp-dir<span class="w"> </span>./lstm_transducer_stateless2/exp<span class="w"> </span><span class="se">\</span>
|
||
<span class="w"> </span>--bpe-model<span class="w"> </span>data/lang_bpe_500/bpe.model<span class="w"> </span><span class="se">\</span>
|
||
<span class="w"> </span>--iter<span class="w"> </span><span class="nv">$iter</span><span class="w"> </span><span class="se">\</span>
|
||
<span class="w"> </span>--avg<span class="w"> </span><span class="nv">$avg</span>
|
||
</pre></div>
|
||
</div>
|
||
<p>It will generate a file <code class="docutils literal notranslate"><span class="pre">./lstm_transducer_stateless2/exp/pretrained.pt</span></code>.</p>
|
||
<div class="admonition hint">
|
||
<p class="admonition-title">Hint</p>
|
||
<p>To use the generated <code class="docutils literal notranslate"><span class="pre">pretrained.pt</span></code> for <code class="docutils literal notranslate"><span class="pre">lstm_transducer_stateless2/decode.py</span></code>,
|
||
you can run:</p>
|
||
<div class="highlight-bash notranslate"><div class="highlight"><pre><span></span><span class="nb">cd</span><span class="w"> </span>lstm_transducer_stateless2/exp
|
||
ln<span class="w"> </span>-s<span class="w"> </span>pretrained<span class="w"> </span>epoch-9999.pt
|
||
</pre></div>
|
||
</div>
|
||
<p>And then pass <code class="docutils literal notranslate"><span class="pre">--epoch</span> <span class="pre">9999</span> <span class="pre">--avg</span> <span class="pre">1</span> <span class="pre">--use-averaged-model</span> <span class="pre">0</span></code> to
|
||
<code class="docutils literal notranslate"><span class="pre">./lstm_transducer_stateless2/decode.py</span></code>.</p>
|
||
</div>
|
||
<p>To use the exported model with <code class="docutils literal notranslate"><span class="pre">./lstm_transducer_stateless2/pretrained.py</span></code>, you
|
||
can run:</p>
|
||
<div class="highlight-bash notranslate"><div class="highlight"><pre><span></span>./lstm_transducer_stateless2/pretrained.py<span class="w"> </span><span class="se">\</span>
|
||
<span class="w"> </span>--checkpoint<span class="w"> </span>./lstm_transducer_stateless2/exp/pretrained.pt<span class="w"> </span><span class="se">\</span>
|
||
<span class="w"> </span>--bpe-model<span class="w"> </span>./data/lang_bpe_500/bpe.model<span class="w"> </span><span class="se">\</span>
|
||
<span class="w"> </span>--method<span class="w"> </span>greedy_search<span class="w"> </span><span class="se">\</span>
|
||
<span class="w"> </span>/path/to/foo.wav<span class="w"> </span><span class="se">\</span>
|
||
<span class="w"> </span>/path/to/bar.wav
|
||
</pre></div>
|
||
</div>
|
||
</section>
|
||
<section id="export-model-using-torch-jit-trace">
|
||
<h3>Export model using <code class="docutils literal notranslate"><span class="pre">torch.jit.trace()</span></code><a class="headerlink" href="#export-model-using-torch-jit-trace" title="Permalink to this heading"></a></h3>
|
||
<div class="highlight-bash notranslate"><div class="highlight"><pre><span></span><span class="nv">iter</span><span class="o">=</span><span class="m">468000</span>
|
||
<span class="nv">avg</span><span class="o">=</span><span class="m">16</span>
|
||
|
||
./lstm_transducer_stateless2/export.py<span class="w"> </span><span class="se">\</span>
|
||
<span class="w"> </span>--exp-dir<span class="w"> </span>./lstm_transducer_stateless2/exp<span class="w"> </span><span class="se">\</span>
|
||
<span class="w"> </span>--bpe-model<span class="w"> </span>data/lang_bpe_500/bpe.model<span class="w"> </span><span class="se">\</span>
|
||
<span class="w"> </span>--iter<span class="w"> </span><span class="nv">$iter</span><span class="w"> </span><span class="se">\</span>
|
||
<span class="w"> </span>--avg<span class="w"> </span><span class="nv">$avg</span><span class="w"> </span><span class="se">\</span>
|
||
<span class="w"> </span>--jit-trace<span class="w"> </span><span class="m">1</span>
|
||
</pre></div>
|
||
</div>
|
||
<p>It will generate 3 files:</p>
|
||
<blockquote>
|
||
<div><ul class="simple">
|
||
<li><p><code class="docutils literal notranslate"><span class="pre">./lstm_transducer_stateless2/exp/encoder_jit_trace.pt</span></code></p></li>
|
||
<li><p><code class="docutils literal notranslate"><span class="pre">./lstm_transducer_stateless2/exp/decoder_jit_trace.pt</span></code></p></li>
|
||
<li><p><code class="docutils literal notranslate"><span class="pre">./lstm_transducer_stateless2/exp/joiner_jit_trace.pt</span></code></p></li>
|
||
</ul>
|
||
</div></blockquote>
|
||
<p>To use the generated files with <code class="docutils literal notranslate"><span class="pre">./lstm_transducer_stateless2/jit_pretrained</span></code>:</p>
|
||
<div class="highlight-bash notranslate"><div class="highlight"><pre><span></span>./lstm_transducer_stateless2/jit_pretrained.py<span class="w"> </span><span class="se">\</span>
|
||
<span class="w"> </span>--bpe-model<span class="w"> </span>./data/lang_bpe_500/bpe.model<span class="w"> </span><span class="se">\</span>
|
||
<span class="w"> </span>--encoder-model-filename<span class="w"> </span>./lstm_transducer_stateless2/exp/encoder_jit_trace.pt<span class="w"> </span><span class="se">\</span>
|
||
<span class="w"> </span>--decoder-model-filename<span class="w"> </span>./lstm_transducer_stateless2/exp/decoder_jit_trace.pt<span class="w"> </span><span class="se">\</span>
|
||
<span class="w"> </span>--joiner-model-filename<span class="w"> </span>./lstm_transducer_stateless2/exp/joiner_jit_trace.pt<span class="w"> </span><span class="se">\</span>
|
||
<span class="w"> </span>/path/to/foo.wav<span class="w"> </span><span class="se">\</span>
|
||
<span class="w"> </span>/path/to/bar.wav
|
||
</pre></div>
|
||
</div>
|
||
<div class="admonition hint">
|
||
<p class="admonition-title">Hint</p>
|
||
<p>Please see <a class="reference external" href="https://k2-fsa.github.io/sherpa/python/streaming_asr/lstm/english/server.html">https://k2-fsa.github.io/sherpa/python/streaming_asr/lstm/english/server.html</a>
|
||
for how to use the exported models in <code class="docutils literal notranslate"><span class="pre">sherpa</span></code>.</p>
|
||
</div>
|
||
</section>
|
||
</section>
|
||
<section id="download-pretrained-models">
|
||
<h2>Download pretrained models<a class="headerlink" href="#download-pretrained-models" title="Permalink to this heading"></a></h2>
|
||
<p>If you don’t want to train from scratch, you can download the pretrained models
|
||
by visiting the following links:</p>
|
||
<blockquote>
|
||
<div><ul class="simple">
|
||
<li><p><a class="reference external" href="https://huggingface.co/csukuangfj/icefall-asr-librispeech-lstm-transducer-stateless2-2022-09-03">https://huggingface.co/csukuangfj/icefall-asr-librispeech-lstm-transducer-stateless2-2022-09-03</a></p></li>
|
||
<li><p><a class="reference external" href="https://huggingface.co/Zengwei/icefall-asr-librispeech-lstm-transducer-stateless-2022-08-18">https://huggingface.co/Zengwei/icefall-asr-librispeech-lstm-transducer-stateless-2022-08-18</a></p></li>
|
||
</ul>
|
||
<p>See <a class="reference external" href="https://github.com/k2-fsa/icefall/blob/master/egs/librispeech/ASR/RESULTS.md">https://github.com/k2-fsa/icefall/blob/master/egs/librispeech/ASR/RESULTS.md</a>
|
||
for the details of the above pretrained models</p>
|
||
</div></blockquote>
|
||
<p>You can find more usages of the pretrained models in
|
||
<a class="reference external" href="https://k2-fsa.github.io/sherpa/python/streaming_asr/lstm/index.html">https://k2-fsa.github.io/sherpa/python/streaming_asr/lstm/index.html</a></p>
|
||
</section>
|
||
</section>
|
||
|
||
|
||
</div>
|
||
</div>
|
||
<footer><div class="rst-footer-buttons" role="navigation" aria-label="Footer">
|
||
<a href="pruned_transducer_stateless.html" class="btn btn-neutral float-left" title="Pruned transducer statelessX" accesskey="p" rel="prev"><span class="fa fa-arrow-circle-left" aria-hidden="true"></span> Previous</a>
|
||
<a href="zipformer_transducer.html" class="btn btn-neutral float-right" title="Zipformer Transducer" 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> |