mirrors/icefall
1
0
Fork 0
mirror of https://github.com/k2-fsa/icefall.git synced 2025-08-09 01:52:41 +00:00
Code Issues Packages Projects Releases Wiki Activity

deploy: 9ae2f3a3c5a3c2336ca236c984843c0e133ee307

Browse Source
This commit is contained in:
csukuangfj 2022-09-21 06:23:20 +00:00
parent 45a5750eda
commit a9ca50fb72
10 changed files with 96 additions and 70 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
.buildinfo
View File

@ -1,4 +1,4 @@
# Sphinx build info version 1 # Sphinx build info version 1
# This file hashes the configuration used when building these files. When it is not found, a full rebuild will be done. # This file hashes the configuration used when building these files. When it is not found, a full rebuild will be done.
config: 3ca2e66d59e42ffdb5e0a5ba2153f99e config: cfc3e6ecc44ed7573f700065af8738a7
tags: 645f666f9bcd5a90fca523b33c5a78b7 tags: 645f666f9bcd5a90fca523b33c5a78b7

73
_sources/recipes/librispeech/lstm_pruned_stateless_transducer.rst.txt
View File

@ -1,5 +1,5 @@
Transducer LSTM Transducer
========== ===============
.. hint:: .. hint::
@ -7,7 +7,7 @@ Transducer
for pretrained models if you don't want to train a model from scratch. for pretrained models if you don't want to train a model from scratch.
This tutorial shows you how to train a transducer model This tutorial shows you how to train an LSTM transducer model
with the `LibriSpeech <https://www.openslr.org/12>`_ dataset. with the `LibriSpeech <https://www.openslr.org/12>`_ dataset.
We use pruned RNN-T to compute the loss. We use pruned RNN-T to compute the loss.
@ -20,9 +20,9 @@ We use pruned RNN-T to compute the loss.
The transducer model consists of 3 parts: The transducer model consists of 3 parts:
- Encoder, a.k.a, transcriber. We use an LSTM model - Encoder, a.k.a, the transcription network. We use an LSTM model
- Decoder, a.k.a, predictor. We use a model consisting of ``nn.Embedding`` - Decoder, a.k.a, the prediction network. We use a stateless model consisting of
and ``nn.Conv1d`` ``nn.Embedding`` and ``nn.Conv1d``
- Joiner, a.k.a, the joint network. - Joiner, a.k.a, the joint network.
.. caution:: .. caution::
@ -74,7 +74,11 @@ Data preparation
The script ``./prepare.sh`` handles the data preparation for you, **automagically**. The script ``./prepare.sh`` handles the data preparation for you, **automagically**.
All you need to do is to run it. All you need to do is to run it.
The data preparation contains several stages, you can use the following two .. note::
We encourage you to read ``./prepare.sh``.
The data preparation contains several stages. You can use the following two
options: options:
- ``--stage`` - ``--stage``
@ -263,7 +267,7 @@ You will find the following files in that directory:
- ``tensorboard/`` - ``tensorboard/``
This folder contains TensorBoard logs. Training loss, validation loss, learning This folder contains tensorBoard logs. Training loss, validation loss, learning
rate, etc, are recorded in these logs. You can visualize them by: rate, etc, are recorded in these logs. You can visualize them by:
.. code-block:: bash .. code-block:: bash
@ -287,7 +291,7 @@ You will find the following files in that directory:
[2022-09-20T15:53:02] Total uploaded: 210171 scalars, 0 tensors, 0 binary objects [2022-09-20T15:53:02] Total uploaded: 210171 scalars, 0 tensors, 0 binary objects
Listening for new data in logdir... Listening for new data in logdir...
Note there is a URL in the above output, click it and you will see Note there is a URL in the above output. Click it and you will see
the following screenshot: the following screenshot:
.. figure:: images/librispeech-lstm-transducer-tensorboard-log.png .. figure:: images/librispeech-lstm-transducer-tensorboard-log.png
@ -422,7 +426,7 @@ The following shows two examples:
Export models Export models
------------- -------------
`lstm_transducer_stateless2/export.py <https://github.com/k2-fsa/icefall/blob/master/egs/librispeech/ASR/lstm_transducer_stateless2/export.py>`_ supports to export checkpoints from ``lstm_transducer_stateless2/exp`` in the following ways. `lstm_transducer_stateless2/export.py <https://github.com/k2-fsa/icefall/blob/master/egs/librispeech/ASR/lstm_transducer_stateless2/export.py>`_ supports exporting checkpoints from ``lstm_transducer_stateless2/exp`` in the following ways.
Export ``model.state_dict()`` Export ``model.state_dict()``
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
@ -458,7 +462,7 @@ It will generate a file ``./lstm_transducer_stateless2/exp/pretrained.pt``.
cd lstm_transducer_stateless2/exp cd lstm_transducer_stateless2/exp
ln -s pretrained epoch-9999.pt ln -s pretrained epoch-9999.pt
And then pass `--epoch 9999 --avg 1 --use-averaged-model 0` to And then pass ``--epoch 9999 --avg 1 --use-averaged-model 0`` to
``./lstm_transducer_stateless2/decode.py``. ``./lstm_transducer_stateless2/decode.py``.
To use the exported model with ``./lstm_transducer_stateless2/pretrained.py``, you To use the exported model with ``./lstm_transducer_stateless2/pretrained.py``, you
@ -506,6 +510,11 @@ To use the generated files with ``./lstm_transducer_stateless2/jit_pretrained``:
/path/to/foo.wav \ /path/to/foo.wav \
/path/to/bar.wav /path/to/bar.wav
.. hint::
Please see `<https://k2-fsa.github.io/sherpa/python/streaming_asr/lstm/english/server.html>`_
for how to use the exported models in ``sherpa``.
Export model for ncnn Export model for ncnn
~~~~~~~~~~~~~~~~~~~~~ ~~~~~~~~~~~~~~~~~~~~~
@ -576,37 +585,37 @@ It will generate the following files:
- ``./lstm_transducer_stateless2/exp/joiner_jit_trace-pnnx.ncnn.param`` - ``./lstm_transducer_stateless2/exp/joiner_jit_trace-pnnx.ncnn.param``
- ``./lstm_transducer_stateless2/exp/joiner_jit_trace-pnnx.ncnn.bin`` - ``./lstm_transducer_stateless2/exp/joiner_jit_trace-pnnx.ncnn.bin``
To use the above generate files, run: To use the above generated files, run:
.. code-block:: bash .. code-block:: bash
./lstm_transducer_stateless2/ncnn-decode.py \ ./lstm_transducer_stateless2/ncnn-decode.py \
--bpe-model-filename ./data/lang_bpe_500/bpe.model \ --bpe-model-filename ./data/lang_bpe_500/bpe.model \
--encoder-param-filename ./lstm_transducer_stateless2/exp/encoder_jit_trace-pnnx.ncnn.param \ --encoder-param-filename ./lstm_transducer_stateless2/exp/encoder_jit_trace-pnnx.ncnn.param \
--encoder-bin-filename ./lstm_transducer_stateless2/exp/encoder_jit_trace-pnnx.ncnn.bin \ --encoder-bin-filename ./lstm_transducer_stateless2/exp/encoder_jit_trace-pnnx.ncnn.bin \
--decoder-param-filename ./lstm_transducer_stateless2/exp/decoder_jit_trace-pnnx.ncnn.param \ --decoder-param-filename ./lstm_transducer_stateless2/exp/decoder_jit_trace-pnnx.ncnn.param \
--decoder-bin-filename ./lstm_transducer_stateless2/exp/decoder_jit_trace-pnnx.ncnn.bin \ --decoder-bin-filename ./lstm_transducer_stateless2/exp/decoder_jit_trace-pnnx.ncnn.bin \
--joiner-param-filename ./lstm_transducer_stateless2/exp/joiner_jit_trace-pnnx.ncnn.param \ --joiner-param-filename ./lstm_transducer_stateless2/exp/joiner_jit_trace-pnnx.ncnn.param \
--joiner-bin-filename ./lstm_transducer_stateless2/exp/joiner_jit_trace-pnnx.ncnn.bin \ --joiner-bin-filename ./lstm_transducer_stateless2/exp/joiner_jit_trace-pnnx.ncnn.bin \
/path/to/foo.wav /path/to/foo.wav
.. code-block:: bash .. code-block:: bash
./lstm_transducer_stateless2/streaming-ncnn-decode.py \ ./lstm_transducer_stateless2/streaming-ncnn-decode.py \
--bpe-model-filename ./data/lang_bpe_500/bpe.model \ --bpe-model-filename ./data/lang_bpe_500/bpe.model \
--encoder-param-filename ./lstm_transducer_stateless2/exp/encoder_jit_trace-pnnx.ncnn.param \ --encoder-param-filename ./lstm_transducer_stateless2/exp/encoder_jit_trace-pnnx.ncnn.param \
--encoder-bin-filename ./lstm_transducer_stateless2/exp/encoder_jit_trace-pnnx.ncnn.bin \ --encoder-bin-filename ./lstm_transducer_stateless2/exp/encoder_jit_trace-pnnx.ncnn.bin \
--decoder-param-filename ./lstm_transducer_stateless2/exp/decoder_jit_trace-pnnx.ncnn.param \ --decoder-param-filename ./lstm_transducer_stateless2/exp/decoder_jit_trace-pnnx.ncnn.param \
--decoder-bin-filename ./lstm_transducer_stateless2/exp/decoder_jit_trace-pnnx.ncnn.bin \ --decoder-bin-filename ./lstm_transducer_stateless2/exp/decoder_jit_trace-pnnx.ncnn.bin \
--joiner-param-filename ./lstm_transducer_stateless2/exp/joiner_jit_trace-pnnx.ncnn.param \ --joiner-param-filename ./lstm_transducer_stateless2/exp/joiner_jit_trace-pnnx.ncnn.param \
--joiner-bin-filename ./lstm_transducer_stateless2/exp/joiner_jit_trace-pnnx.ncnn.bin \ --joiner-bin-filename ./lstm_transducer_stateless2/exp/joiner_jit_trace-pnnx.ncnn.bin \
/path/to/foo.wav /path/to/foo.wav
To use the above generated files in C++, please see To use the above generated files in C++, please see
`<https://github.com/k2-fsa/sherpa-ncnn>`_ `<https://github.com/k2-fsa/sherpa-ncnn>`_
It is able to generate a static linked library that can be run on Linux, Windows, It is able to generate a static linked executable that can be run on Linux, Windows,
macOS, Raspberry Pi, etc. macOS, Raspberry Pi, etc, without external dependencies.
Download pretrained models Download pretrained models
-------------------------- --------------------------

BIN
objects.inv
View File

Binary file not shown.

2
recipes/index.html
View File

@ -93,7 +93,7 @@ Currently, only speech recognition recipes are provided.</p>
<li class="toctree-l1"><a class="reference internal" href="librispeech/index.html">LibriSpeech</a><ul> <li class="toctree-l1"><a class="reference internal" href="librispeech/index.html">LibriSpeech</a><ul>
<li class="toctree-l2"><a class="reference internal" href="librispeech/tdnn_lstm_ctc.html">TDNN-LSTM-CTC</a></li> <li class="toctree-l2"><a class="reference internal" href="librispeech/tdnn_lstm_ctc.html">TDNN-LSTM-CTC</a></li>
<li class="toctree-l2"><a class="reference internal" href="librispeech/conformer_ctc.html">Conformer CTC</a></li> <li class="toctree-l2"><a class="reference internal" href="librispeech/conformer_ctc.html">Conformer CTC</a></li>
<li class="toctree-l2"><a class="reference internal" href="librispeech/lstm_pruned_stateless_transducer.html">Transducer</a></li> <li class="toctree-l2"><a class="reference internal" href="librispeech/lstm_pruned_stateless_transducer.html">LSTM Transducer</a></li>
</ul> </ul>
</li> </li>
<li class="toctree-l1"><a class="reference internal" href="timit/index.html">TIMIT</a><ul> <li class="toctree-l1"><a class="reference internal" href="timit/index.html">TIMIT</a><ul>

6
recipes/librispeech/conformer_ctc.html
View File

@ -19,7 +19,7 @@
<script src="../../_static/js/theme.js"></script> <script src="../../_static/js/theme.js"></script>
<link rel="index" title="Index" href="../../genindex.html" /> <link rel="index" title="Index" href="../../genindex.html" />
<link rel="search" title="Search" href="../../search.html" /> <link rel="search" title="Search" href="../../search.html" />
<link rel="next" title="Transducer" href="lstm_pruned_stateless_transducer.html" /> <link rel="next" title="LSTM Transducer" href="lstm_pruned_stateless_transducer.html" />
<link rel="prev" title="TDNN-LSTM-CTC" href="tdnn_lstm_ctc.html" /> <link rel="prev" title="TDNN-LSTM-CTC" href="tdnn_lstm_ctc.html" />
</head> </head>
@ -54,7 +54,7 @@
<li class="toctree-l4"><a class="reference internal" href="#deployment-with-c">Deployment with C++</a></li> <li class="toctree-l4"><a class="reference internal" href="#deployment-with-c">Deployment with C++</a></li>
</ul> </ul>
</li> </li>
<li class="toctree-l3"><a class="reference internal" href="lstm_pruned_stateless_transducer.html">Transducer</a></li> <li class="toctree-l3"><a class="reference internal" href="lstm_pruned_stateless_transducer.html">LSTM Transducer</a></li>
</ul> </ul>
</li> </li>
<li class="toctree-l2"><a class="reference internal" href="../timit/index.html">TIMIT</a></li> <li class="toctree-l2"><a class="reference internal" href="../timit/index.html">TIMIT</a></li>
@ -1087,7 +1087,7 @@ Please see <a class="reference external" href="https://colab.research.google.com
</div> </div>
<footer><div class="rst-footer-buttons" role="navigation" aria-label="Footer"> <footer><div class="rst-footer-buttons" role="navigation" aria-label="Footer">
<a href="tdnn_lstm_ctc.html" class="btn btn-neutral float-left" title="TDNN-LSTM-CTC" accesskey="p" rel="prev"><span class="fa fa-arrow-circle-left" aria-hidden="true"></span> Previous</a> <a href="tdnn_lstm_ctc.html" class="btn btn-neutral float-left" title="TDNN-LSTM-CTC" accesskey="p" rel="prev"><span class="fa fa-arrow-circle-left" aria-hidden="true"></span> Previous</a>
<a href="lstm_pruned_stateless_transducer.html" class="btn btn-neutral float-right" title="Transducer" accesskey="n" rel="next">Next <span class="fa fa-arrow-circle-right" aria-hidden="true"></span></a> <a href="lstm_pruned_stateless_transducer.html" class="btn btn-neutral float-right" title="LSTM Transducer" accesskey="n" rel="next">Next <span class="fa fa-arrow-circle-right" aria-hidden="true"></span></a>
</div> </div>
<hr/> <hr/>

4
recipes/librispeech/index.html
View File

@ -46,7 +46,7 @@
<li class="toctree-l2 current"><a class="current reference internal" href="#">LibriSpeech</a><ul> <li class="toctree-l2 current"><a class="current reference internal" href="#">LibriSpeech</a><ul>
<li class="toctree-l3"><a class="reference internal" href="tdnn_lstm_ctc.html">TDNN-LSTM-CTC</a></li> <li class="toctree-l3"><a class="reference internal" href="tdnn_lstm_ctc.html">TDNN-LSTM-CTC</a></li>
<li class="toctree-l3"><a class="reference internal" href="conformer_ctc.html">Conformer CTC</a></li> <li class="toctree-l3"><a class="reference internal" href="conformer_ctc.html">Conformer CTC</a></li>
<li class="toctree-l3"><a class="reference internal" href="lstm_pruned_stateless_transducer.html">Transducer</a></li> <li class="toctree-l3"><a class="reference internal" href="lstm_pruned_stateless_transducer.html">LSTM Transducer</a></li>
</ul> </ul>
</li> </li>
<li class="toctree-l2"><a class="reference internal" href="../timit/index.html">TIMIT</a></li> <li class="toctree-l2"><a class="reference internal" href="../timit/index.html">TIMIT</a></li>
@ -88,7 +88,7 @@
<ul> <ul>
<li class="toctree-l1"><a class="reference internal" href="tdnn_lstm_ctc.html">TDNN-LSTM-CTC</a></li> <li class="toctree-l1"><a class="reference internal" href="tdnn_lstm_ctc.html">TDNN-LSTM-CTC</a></li>
<li class="toctree-l1"><a class="reference internal" href="conformer_ctc.html">Conformer CTC</a></li> <li class="toctree-l1"><a class="reference internal" href="conformer_ctc.html">Conformer CTC</a></li>
<li class="toctree-l1"><a class="reference internal" href="lstm_pruned_stateless_transducer.html">Transducer</a></li> <li class="toctree-l1"><a class="reference internal" href="lstm_pruned_stateless_transducer.html">LSTM Transducer</a></li>
</ul> </ul>
</div> </div>
</section> </section>

71
recipes/librispeech/lstm_pruned_stateless_transducer.html
View File

@ -4,7 +4,7 @@
<meta charset="utf-8" /><meta name="generator" content="Docutils 0.17.1: http://docutils.sourceforge.net/" /> <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" /> <meta name="viewport" content="width=device-width, initial-scale=1.0" />
<title>Transducer &mdash; icefall 0.1 documentation</title> <title>LSTM Transducer &mdash; icefall 0.1 documentation</title>
<link rel="stylesheet" href="../../_static/pygments.css" type="text/css" /> <link rel="stylesheet" href="../../_static/pygments.css" type="text/css" />
<link rel="stylesheet" href="../../_static/css/theme.css" type="text/css" /> <link rel="stylesheet" href="../../_static/css/theme.css" type="text/css" />
<!--[if lt IE 9]> <!--[if lt IE 9]>
@ -46,7 +46,7 @@
<li class="toctree-l2 current"><a class="reference internal" href="index.html">LibriSpeech</a><ul class="current"> <li class="toctree-l2 current"><a class="reference internal" href="index.html">LibriSpeech</a><ul class="current">
<li class="toctree-l3"><a class="reference internal" href="tdnn_lstm_ctc.html">TDNN-LSTM-CTC</a></li> <li class="toctree-l3"><a class="reference internal" href="tdnn_lstm_ctc.html">TDNN-LSTM-CTC</a></li>
<li class="toctree-l3"><a class="reference internal" href="conformer_ctc.html">Conformer CTC</a></li> <li class="toctree-l3"><a class="reference internal" href="conformer_ctc.html">Conformer CTC</a></li>
<li class="toctree-l3 current"><a class="current reference internal" href="#">Transducer</a><ul> <li class="toctree-l3 current"><a class="current reference internal" href="#">LSTM Transducer</a><ul>
<li class="toctree-l4"><a class="reference internal" href="#which-model-to-use">Which model to use</a></li> <li class="toctree-l4"><a class="reference internal" href="#which-model-to-use">Which model to use</a></li>
<li class="toctree-l4"><a class="reference internal" href="#data-preparation">Data preparation</a></li> <li class="toctree-l4"><a class="reference internal" href="#data-preparation">Data preparation</a></li>
<li class="toctree-l4"><a class="reference internal" href="#training">Training</a></li> <li class="toctree-l4"><a class="reference internal" href="#training">Training</a></li>
@ -81,7 +81,7 @@
<li><a href="../../index.html" class="icon icon-home"></a> &raquo;</li> <li><a href="../../index.html" class="icon icon-home"></a> &raquo;</li>
<li><a href="../index.html">Recipes</a> &raquo;</li> <li><a href="../index.html">Recipes</a> &raquo;</li>
<li><a href="index.html">LibriSpeech</a> &raquo;</li> <li><a href="index.html">LibriSpeech</a> &raquo;</li>
<li>Transducer</li> <li>LSTM Transducer</li>
<li class="wy-breadcrumbs-aside"> <li class="wy-breadcrumbs-aside">
<a href="https://github.com/k2-fsa/icefall/blob/master/icefall/docs/source/recipes/librispeech/lstm_pruned_stateless_transducer.rst" class="fa fa-github"> Edit on GitHub</a> <a href="https://github.com/k2-fsa/icefall/blob/master/icefall/docs/source/recipes/librispeech/lstm_pruned_stateless_transducer.rst" class="fa fa-github"> Edit on GitHub</a>
</li> </li>
@ -91,14 +91,14 @@
<div role="main" class="document" itemscope="itemscope" itemtype="http://schema.org/Article"> <div role="main" class="document" itemscope="itemscope" itemtype="http://schema.org/Article">
<div itemprop="articleBody"> <div itemprop="articleBody">
<section id="transducer"> <section id="lstm-transducer">
<h1>Transducer<a class="headerlink" href="#transducer" title="Permalink to this heading"></a></h1> <h1>LSTM Transducer<a class="headerlink" href="#lstm-transducer" title="Permalink to this heading"></a></h1>
<div class="admonition hint"> <div class="admonition hint">
<p class="admonition-title">Hint</p> <p class="admonition-title">Hint</p>
<p>Please scroll down to the bottom of this page to find download links <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> for pretrained models if you don’t want to train a model from scratch.</p>
</div> </div>
<p>This tutorial shows you how to train a transducer model <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> 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> <p>We use pruned RNN-T to compute the loss.</p>
<div class="admonition note"> <div class="admonition note">
@ -109,9 +109,9 @@ with the <a class="reference external" href="https://www.openslr.org/12">LibriSp
<p>The transducer model consists of 3 parts:</p> <p>The transducer model consists of 3 parts:</p>
<blockquote> <blockquote>
<div><ul class="simple"> <div><ul class="simple">
<li><p>Encoder, a.k.a, transcriber. We use an LSTM model</p></li> <li><p>Encoder, a.k.a, the transcription network. We use an LSTM model</p></li>
<li><p>Decoder, a.k.a, predictor. We use a model consisting of <code class="docutils literal notranslate"><span class="pre">nn.Embedding</span></code> <li><p>Decoder, a.k.a, the prediction network. We use a stateless model consisting of
and <code class="docutils literal notranslate"><span class="pre">nn.Conv1d</span></code></p></li> <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> <li><p>Joiner, a.k.a, the joint network.</p></li>
</ul> </ul>
</div></blockquote> </div></blockquote>
@ -159,7 +159,11 @@ $ ./prepare_giga_speech.sh
</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>. <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> All you need to do is to run it.</p>
<p>The data preparation contains several stages, you can use the following two <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> options:</p>
<blockquote> <blockquote>
<div><ul class="simple"> <div><ul class="simple">
@ -344,7 +348,7 @@ To resume training from some checkpoint, say <code class="docutils literal notra
</div></blockquote> </div></blockquote>
</li> </li>
<li><p><code class="docutils literal notranslate"><span class="pre">tensorboard/</span></code></p> <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 <p>This folder contains tensorBoard logs. Training loss, validation loss, learning
rate, etc, are recorded in these logs. You can visualize them by:</p> rate, etc, are recorded in these logs. You can visualize them by:</p>
<blockquote> <blockquote>
<div><div class="highlight-bash notranslate"><div class="highlight"><pre><span></span>$ <span class="nb">cd</span> lstm_transducer_stateless2/exp/tensorboard <div><div class="highlight-bash notranslate"><div class="highlight"><pre><span></span>$ <span class="nb">cd</span> lstm_transducer_stateless2/exp/tensorboard
@ -368,7 +372,7 @@ $ tensorboard dev upload --logdir . --description <span class="s2">&quot;LSTM tr
</pre></div> </pre></div>
</div> </div>
</div></blockquote> </div></blockquote>
<p>Note there is a URL in the above output, click it and you will see <p>Note there is a URL in the above output. Click it and you will see
the following screenshot:</p> the following screenshot:</p>
<blockquote> <blockquote>
<div><figure class="align-center" id="id2"> <div><figure class="align-center" id="id2">
@ -498,7 +502,7 @@ $ ./lstm_transducer_stateless2/decode.py --help
</section> </section>
<section id="export-models"> <section id="export-models">
<h2>Export models<a class="headerlink" href="#export-models" title="Permalink to this heading"></a></h2> <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 to export checkpoints from <code class="docutils literal notranslate"><span class="pre">lstm_transducer_stateless2/exp</span></code> in the following ways.</p> <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"> <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> <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 <p>Checkpoints saved by <code class="docutils literal notranslate"><span class="pre">lstm_transducer_stateless2/train.py</span></code> also include
@ -527,7 +531,7 @@ you can run:</p>
ln -s pretrained epoch-9999.pt ln -s pretrained epoch-9999.pt
</pre></div> </pre></div>
</div> </div>
<p>And then pass <cite>–epoch 9999 –avg 1 –use-averaged-model 0</cite> to <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> <code class="docutils literal notranslate"><span class="pre">./lstm_transducer_stateless2/decode.py</span></code>.</p>
</div> </div>
<p>To use the exported model with <code class="docutils literal notranslate"><span class="pre">./lstm_transducer_stateless2/pretrained.py</span></code>, you <p>To use the exported model with <code class="docutils literal notranslate"><span class="pre">./lstm_transducer_stateless2/pretrained.py</span></code>, you
@ -572,6 +576,11 @@ can run:</p>
/path/to/bar.wav /path/to/bar.wav
</pre></div> </pre></div>
</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="export-model-for-ncnn"> <section id="export-model-for-ncnn">
<h3>Export model for ncnn<a class="headerlink" href="#export-model-for-ncnn" title="Permalink to this heading"></a></h3> <h3>Export model for ncnn<a class="headerlink" href="#export-model-for-ncnn" title="Permalink to this heading"></a></h3>
@ -639,25 +648,33 @@ for <code class="docutils literal notranslate"><span class="pre">pnnx</span></co
<li><p><code class="docutils literal notranslate"><span class="pre">./lstm_transducer_stateless2/exp/joiner_jit_trace-pnnx.ncnn.bin</span></code></p></li> <li><p><code class="docutils literal notranslate"><span class="pre">./lstm_transducer_stateless2/exp/joiner_jit_trace-pnnx.ncnn.bin</span></code></p></li>
</ul> </ul>
</div></blockquote> </div></blockquote>
<p>To use the above generate files, run:</p> <p>To use the above generated files, run:</p>
<div class="highlight-bash notranslate"><div class="highlight"><pre><span></span> <div class="highlight-bash notranslate"><div class="highlight"><pre><span></span>./lstm_transducer_stateless2/ncnn-decode.py <span class="se">\</span>
--bpe-model-filename ./data/lang_bpe_500/bpe.model <span class="se">\</span>
--encoder-param-filename ./lstm_transducer_stateless2/exp/encoder_jit_trace-pnnx.ncnn.param <span class="se">\</span>
--encoder-bin-filename ./lstm_transducer_stateless2/exp/encoder_jit_trace-pnnx.ncnn.bin <span class="se">\</span>
--decoder-param-filename ./lstm_transducer_stateless2/exp/decoder_jit_trace-pnnx.ncnn.param <span class="se">\</span>
--decoder-bin-filename ./lstm_transducer_stateless2/exp/decoder_jit_trace-pnnx.ncnn.bin <span class="se">\</span>
--joiner-param-filename ./lstm_transducer_stateless2/exp/joiner_jit_trace-pnnx.ncnn.param <span class="se">\</span>
--joiner-bin-filename ./lstm_transducer_stateless2/exp/joiner_jit_trace-pnnx.ncnn.bin <span class="se">\</span>
/path/to/foo.wav
</pre></div> </pre></div>
</div> </div>
<dl class="simple"> <div class="highlight-bash notranslate"><div class="highlight"><pre><span></span>./lstm_transducer_stateless2/streaming-ncnn-decode.py <span class="se">\</span>
<dt>./lstm_transducer_stateless2/ncnn-decode.py </dt><dd><p>–bpe-model-filename ./data/lang_bpe_500/bpe.model –encoder-param-filename ./lstm_transducer_stateless2/exp/encoder_jit_trace-pnnx.ncnn.param –encoder-bin-filename ./lstm_transducer_stateless2/exp/encoder_jit_trace-pnnx.ncnn.bin –decoder-param-filename ./lstm_transducer_stateless2/exp/decoder_jit_trace-pnnx.ncnn.param –decoder-bin-filename ./lstm_transducer_stateless2/exp/decoder_jit_trace-pnnx.ncnn.bin –joiner-param-filename ./lstm_transducer_stateless2/exp/joiner_jit_trace-pnnx.ncnn.param –joiner-bin-filename ./lstm_transducer_stateless2/exp/joiner_jit_trace-pnnx.ncnn.bin /path/to/foo.wav</p> --bpe-model-filename ./data/lang_bpe_500/bpe.model <span class="se">\</span>
</dd> --encoder-param-filename ./lstm_transducer_stateless2/exp/encoder_jit_trace-pnnx.ncnn.param <span class="se">\</span>
</dl> --encoder-bin-filename ./lstm_transducer_stateless2/exp/encoder_jit_trace-pnnx.ncnn.bin <span class="se">\</span>
<div class="highlight-bash notranslate"><div class="highlight"><pre><span></span> --decoder-param-filename ./lstm_transducer_stateless2/exp/decoder_jit_trace-pnnx.ncnn.param <span class="se">\</span>
--decoder-bin-filename ./lstm_transducer_stateless2/exp/decoder_jit_trace-pnnx.ncnn.bin <span class="se">\</span>
--joiner-param-filename ./lstm_transducer_stateless2/exp/joiner_jit_trace-pnnx.ncnn.param <span class="se">\</span>
--joiner-bin-filename ./lstm_transducer_stateless2/exp/joiner_jit_trace-pnnx.ncnn.bin <span class="se">\</span>
/path/to/foo.wav
</pre></div> </pre></div>
</div> </div>
<dl class="simple">
<dt>./lstm_transducer_stateless2/streaming-ncnn-decode.py </dt><dd><p>–bpe-model-filename ./data/lang_bpe_500/bpe.model –encoder-param-filename ./lstm_transducer_stateless2/exp/encoder_jit_trace-pnnx.ncnn.param –encoder-bin-filename ./lstm_transducer_stateless2/exp/encoder_jit_trace-pnnx.ncnn.bin –decoder-param-filename ./lstm_transducer_stateless2/exp/decoder_jit_trace-pnnx.ncnn.param –decoder-bin-filename ./lstm_transducer_stateless2/exp/decoder_jit_trace-pnnx.ncnn.bin –joiner-param-filename ./lstm_transducer_stateless2/exp/joiner_jit_trace-pnnx.ncnn.param –joiner-bin-filename ./lstm_transducer_stateless2/exp/joiner_jit_trace-pnnx.ncnn.bin /path/to/foo.wav</p>
</dd>
</dl>
<p>To use the above generated files in C++, please see <p>To use the above generated files in C++, please see
<a class="reference external" href="https://github.com/k2-fsa/sherpa-ncnn">https://github.com/k2-fsa/sherpa-ncnn</a></p> <a class="reference external" href="https://github.com/k2-fsa/sherpa-ncnn">https://github.com/k2-fsa/sherpa-ncnn</a></p>
<p>It is able to generate a static linked library that can be run on Linux, Windows, <p>It is able to generate a static linked executable that can be run on Linux, Windows,
macOS, Raspberry Pi, etc.</p> macOS, Raspberry Pi, etc, without external dependencies.</p>
</section> </section>
</section> </section>
<section id="download-pretrained-models"> <section id="download-pretrained-models">

2
recipes/librispeech/tdnn_lstm_ctc.html
View File

@ -53,7 +53,7 @@
</ul> </ul>
</li> </li>
<li class="toctree-l3"><a class="reference internal" href="conformer_ctc.html">Conformer CTC</a></li> <li class="toctree-l3"><a class="reference internal" href="conformer_ctc.html">Conformer CTC</a></li>
<li class="toctree-l3"><a class="reference internal" href="lstm_pruned_stateless_transducer.html">Transducer</a></li> <li class="toctree-l3"><a class="reference internal" href="lstm_pruned_stateless_transducer.html">LSTM Transducer</a></li>
</ul> </ul>
</li> </li>
<li class="toctree-l2"><a class="reference internal" href="../timit/index.html">TIMIT</a></li> <li class="toctree-l2"><a class="reference internal" href="../timit/index.html">TIMIT</a></li>

4
recipes/timit/index.html
View File

@ -20,7 +20,7 @@
<link rel="index" title="Index" href="../../genindex.html" /> <link rel="index" title="Index" href="../../genindex.html" />
<link rel="search" title="Search" href="../../search.html" /> <link rel="search" title="Search" href="../../search.html" />
<link rel="next" title="TDNN-LiGRU-CTC" href="tdnn_ligru_ctc.html" /> <link rel="next" title="TDNN-LiGRU-CTC" href="tdnn_ligru_ctc.html" />
<link rel="prev" title="Transducer" href="../librispeech/lstm_pruned_stateless_transducer.html" /> <link rel="prev" title="LSTM Transducer" href="../librispeech/lstm_pruned_stateless_transducer.html" />
</head> </head>
<body class="wy-body-for-nav"> <body class="wy-body-for-nav">
@ -95,7 +95,7 @@
</div> </div>
</div> </div>
<footer><div class="rst-footer-buttons" role="navigation" aria-label="Footer"> <footer><div class="rst-footer-buttons" role="navigation" aria-label="Footer">
<a href="../librispeech/lstm_pruned_stateless_transducer.html" class="btn btn-neutral float-left" title="Transducer" accesskey="p" rel="prev"><span class="fa fa-arrow-circle-left" aria-hidden="true"></span> Previous</a> <a href="../librispeech/lstm_pruned_stateless_transducer.html" class="btn btn-neutral float-left" title="LSTM Transducer" accesskey="p" rel="prev"><span class="fa fa-arrow-circle-left" aria-hidden="true"></span> Previous</a>
<a href="tdnn_ligru_ctc.html" class="btn btn-neutral float-right" title="TDNN-LiGRU-CTC" accesskey="n" rel="next">Next <span class="fa fa-arrow-circle-right" aria-hidden="true"></span></a> <a href="tdnn_ligru_ctc.html" class="btn btn-neutral float-right" title="TDNN-LiGRU-CTC" accesskey="n" rel="next">Next <span class="fa fa-arrow-circle-right" aria-hidden="true"></span></a>
</div> </div>

2
searchindex.js
View File

File diff suppressed because one or more lines are too long