deploy: 5c8e9628cc39b9fb1e471d53df9aec06b2602b97

_sources/faqs.rst.txt

@@ -65,3 +65,43 @@ The fix is:
   pip uninstall setuptools
 
   pip install setuptools==58.0.4
+
+ImportError: libpython3.10.so.1.0: cannot open shared object file: No such file or directory
+--------------------------------------------------------------------------------------------
+
+If you are using ``conda`` and encounter the following issue:
+
+.. code-block::
+
+  Traceback (most recent call last):
+    File "/k2-dev/yangyifan/anaconda3/envs/icefall/lib/python3.10/site-packages/k2-1.23.3.dev20230112+cuda11.6.torch1.13.1-py3.10-linux-x86_64.egg/k2/__init__.py", line 24, in <module>
+      from _k2 import DeterminizeWeightPushingType
+  ImportError: libpython3.10.so.1.0: cannot open shared object file: No such file or directory
+
+  During handling of the above exception, another exception occurred:
+
+  Traceback (most recent call last):
+    File "/k2-dev/yangyifan/icefall/egs/librispeech/ASR/./pruned_transducer_stateless7_ctc_bs/decode.py", line 104, in <module>
+      import k2
+    File "/k2-dev/yangyifan/anaconda3/envs/icefall/lib/python3.10/site-packages/k2-1.23.3.dev20230112+cuda11.6.torch1.13.1-py3.10-linux-x86_64.egg/k2/__init__.py", line 30, in <module>
+      raise ImportError(
+  ImportError: libpython3.10.so.1.0: cannot open shared object file: No such file or directory
+  Note: If you're using anaconda and importing k2 on MacOS,
+        you can probably fix this by setting the environment variable:
+    export DYLD_LIBRARY_PATH=$CONDA_PREFIX/lib/python3.10/site-packages:$DYLD_LIBRARY_PATH
+
+Please first try to find where ``libpython3.10.so.1.0`` locates.
+
+For instance,
+
+.. code-block:: bash
+
+  cd $CONDA_PREFIX/lib
+  find . -name "libpython*"
+
+If you are able to find it inside ``$CODNA_PREFIX/lib``, please set the
+following environment variable:
+
+.. code-block:: bash
+
+  export LD_LIBRARY_PATH=$CONDA_PREFIX/lib:$LD_LIBRARY_PATH

_sources/recipes/Non-streaming-ASR/librispeech/distillation.rst.txt

@@ -1,16 +1,16 @@
 Distillation with HuBERT
 ========================
 
-This totorial shows you how to perform knowledge distillation in ``icefall`` 
-with the `LibriSpeech <https://www.openslr.org/12>`_ dataset. The distillation method
-used here is called "Multi Vector Quantization Knowledge Distillation" (MVQ-KD). 
+This tutorial shows you how to perform knowledge distillation in `icefall`_
+with the `LibriSpeech`_ dataset. The distillation method
+used here is called "Multi Vector Quantization Knowledge Distillation" (MVQ-KD).
 Please have a look at our paper `Predicting Multi-Codebook Vector Quantization Indexes for Knowledge Distillation <https://arxiv.org/abs/2211.00508>`_
 for more details about MVQ-KD.
 
 .. note::
 
     This tutorial is based on recipe
-     `pruned_transducer_stateless4 <https://github.com/k2-fsa/icefall/tree/master/egs/librispeech/ASR/pruned_transducer_stateless4>`_.
+    `pruned_transducer_stateless4 <https://github.com/k2-fsa/icefall/tree/master/egs/librispeech/ASR/pruned_transducer_stateless4>`_.
     Currently, we only implement MVQ-KD in this recipe. However, MVQ-KD is theoretically applicable to all recipes
     with only minor changes needed. Feel free to try out MVQ-KD in different recipes. If you
     encounter any problems, please open an issue here `icefall <https://github.com/k2-fsa/icefall/issues>`_.
@@ -18,7 +18,7 @@ for more details about MVQ-KD.
 .. note::
 
   We assume you have read the page :ref:`install icefall` and have setup
-  the environment for ``icefall``.
+  the environment for `icefall`_.
 
 .. HINT::
 
@@ -27,13 +27,13 @@ for more details about MVQ-KD.
 Data preparation
 ----------------
 
-We first prepare necessary training data for ``LibriSpeech``. 
-This is the same as in `Pruned_transducer_statelessX <./pruned_transducer_stateless.rst>`_.
+We first prepare necessary training data for `LibriSpeech`_.
+This is the same as in :ref:`non_streaming_librispeech_pruned_transducer_stateless`.
 
 .. hint::
 
    The data preparation is the same as other recipes on LibriSpeech dataset,
-   if you have finished this step, you can skip to ``Codebook index preparation`` directly.
+   if you have finished this step, you can skip to :ref:`codebook_index_preparation` directly.
 
 .. code-block:: bash
 
@@ -61,8 +61,8 @@ For example,
 
 .. HINT::
 
-  If you have pre-downloaded the `LibriSpeech <https://www.openslr.org/12>`_
-  dataset and the `musan <http://www.openslr.org/17/>`_ dataset, say,
+  If you have pre-downloaded the `LibriSpeech`_
+  dataset and the `musan`_ dataset, say,
   they are saved in ``/tmp/LibriSpeech`` and ``/tmp/musan``, you can modify
   the ``dl_dir`` variable in ``./prepare.sh`` to point to ``/tmp`` so that
   ``./prepare.sh`` won't re-download them.
@@ -84,24 +84,27 @@ We provide the following YouTube video showing how to run ``./prepare.sh``.
 ..  youtube:: ofEIoJL-mGM
 
 
+.. _codebook_index_preparation:
+
 Codebook index preparation
 --------------------------
 
 Here, we prepare necessary data for MVQ-KD. This requires the generation
 of codebook indexes (please read our `paper <https://arxiv.org/abs/2211.00508>`_.
-if you are interested in details). In this tutorial, we use the pre-computed 
-codebook indexes for convenience. The only thing you need to do is to 
-run ``./distillation_with_hubert.sh``. 
+if you are interested in details). In this tutorial, we use the pre-computed
+codebook indexes for convenience. The only thing you need to do is to
+run `./distillation_with_hubert.sh <https://github.com/k2-fsa/icefall/blob/master/egs/librispeech/ASR/distillation_with_hubert.sh>`_.
 
 .. note::
-  There are 5 stages in total, the first and second stage will be automatically skipped 
-  when choosing to downloaded codebook indexes prepared by `icefall`_. 
-  Of course, you can extract and compute the codebook indexes by yourself. This 
-  will require you downloading a HuBERT-XL model and it can take a while for 
-  the extraction of codebook indexes.
-  
 
-As usual, you can control the stages you want to run by specifying the following 
+  There are 5 stages in total, the first and second stage will be automatically skipped
+  when choosing to downloaded codebook indexes prepared by `icefall`_.
+  Of course, you can extract and compute the codebook indexes by yourself. This
+  will require you downloading a HuBERT-XL model and it can take a while for
+  the extraction of codebook indexes.
+
+
+As usual, you can control the stages you want to run by specifying the following
 two options:
 
   - ``--stage``
@@ -115,7 +118,7 @@ For example,
   $ ./distillation_with_hubert.sh --stage 0 --stop-stage 0 # run only stage 0
   $ ./distillation_with_hubert.sh --stage 2 --stop-stage 4 # run from stage 2 to stage 5
 
-Here are a few options in ``./distillation_with_hubert.sh`` 
+Here are a few options in `./distillation_with_hubert.sh <https://github.com/k2-fsa/icefall/blob/master/egs/librispeech/ASR/distillation_with_hubert.sh>`_
 you need to know before you proceed.
 
 - ``--full_libri`` If True, use full 960h data. Otherwise only ``train-clean-100`` will be used
@@ -126,14 +129,14 @@ Since we are using the pre-computed codebook indexes, we set
 ``use_extracted_codebook=True``. If you want to do full `LibriSpeech`_
 experiments, please set ``full_libri=True``.
 
-The following command downloads the pre-computed codebook indexes 
-and prepares MVQ-augmented training manifests. 
+The following command downloads the pre-computed codebook indexes
+and prepares MVQ-augmented training manifests.
 
 .. code-block:: bash
 
   $ ./distillation_with_hubert.sh --stage 2 --stop-stage 2 # run only stage 2
 
-Please see the 
+Please see the
 following screenshot for the output of an example execution.
 
 .. figure:: ./images/distillation_codebook.png
@@ -146,12 +149,12 @@ following screenshot for the output of an example execution.
 .. hint::
 
   The codebook indexes we prepared for you in this tutorial
-  are extracted from the 36-th layer of a fine-tuned HuBERT-XL model 
+  are extracted from the 36-th layer of a fine-tuned HuBERT-XL model
   with 8 codebooks. If you want to try other configurations, please
-  set ``use_extracted_codebook=False`` and set ``embedding_layer`` and 
+  set ``use_extracted_codebook=False`` and set ``embedding_layer`` and
   ``num_codebooks`` by yourself.
 
-Now, you should see the following files under the direcory ``./data/vq_fbank_layer36_cb8``.
+Now, you should see the following files under the directory ``./data/vq_fbank_layer36_cb8``.
 
 .. figure:: ./images/distillation_directory.png
   :width: 800
@@ -165,7 +168,7 @@ Whola! You are ready to perform knowledge distillation training now!
 Training
 --------
 
-To perform training, please run stage 3 by executing the following command. 
+To perform training, please run stage 3 by executing the following command.
 
 .. code-block:: bash
 
@@ -176,7 +179,7 @@ Here is the code snippet for training:
 .. code-block:: bash
 
   WORLD_SIZE=$(echo ${CUDA_VISIBLE_DEVICES} | awk '{n=split($1, _, ","); print n}')
-  
+
   ./pruned_transducer_stateless6/train.py \
     --manifest-dir ./data/vq_fbank_layer36_cb8 \
     --master-port 12359 \
@@ -191,6 +194,7 @@ Here is the code snippet for training:
 
 There are a few training arguments in the following
 training commands that should be paid attention to.
+
   - ``--enable-distillation`` If True, knowledge distillation training is enabled.
   - ``--codebook-loss-scale`` The scale of the knowledge distillation loss.
   - ``--manifest-dir`` The path to the MVQ-augmented manifest.
@@ -204,7 +208,7 @@ the following command.
 
 .. code-block:: bash
 
-  export CUDA_VISIBLE_DEVICES=0  
+  export CUDA_VISIBLE_DEVICES=0
   ./pruned_transducer_stateless6/train.py \
     --decoding-method "modified_beam_search" \
     --epoch 30 \
@@ -217,4 +221,3 @@ You should get similar results as `here <https://github.com/k2-fsa/icefall/blob/
 
 That's all! Feel free to experiment with your own setups and report your results.
 If you encounter any problems during training, please open up an issue `here <https://github.com/k2-fsa/icefall/issues>`_.
-

_sources/recipes/Non-streaming-ASR/librispeech/pruned_transducer_stateless.rst.txt

@@ -1,3 +1,5 @@
+.. _non_streaming_librispeech_pruned_transducer_stateless:
+
 Pruned transducer statelessX
 ============================
 

faqs.html

@@ -45,6 +45,7 @@
 <li class="toctree-l1 current"><a class="current reference internal" href="#">Frequently Asked Questions (FAQs)</a><ul>
 <li class="toctree-l2"><a class="reference internal" href="#oserror-libtorch-hip-so-cannot-open-shared-object-file-no-such-file-or-directory">OSError: libtorch_hip.so: cannot open shared object file: no such file or directory</a></li>
 <li class="toctree-l2"><a class="reference internal" href="#attributeerror-module-distutils-has-no-attribute-version">AttributeError: module ‘distutils’ has no attribute ‘version’</a></li>
+<li class="toctree-l2"><a class="reference internal" href="#importerror-libpython3-10-so-1-0-cannot-open-shared-object-file-no-such-file-or-directory">ImportError: libpython3.10.so.1.0: cannot open shared object file: No such file or directory</a></li>
 </ul>
 </li>
 <li class="toctree-l1"><a class="reference internal" href="model-export/index.html">Model export</a></li>
@@ -136,6 +137,39 @@ pip<span class="w"> </span>install<span class="w"> </span><span class="nv">setup
 </pre></div>
 </div>
 </section>
+<section id="importerror-libpython3-10-so-1-0-cannot-open-shared-object-file-no-such-file-or-directory">
+<h2>ImportError: libpython3.10.so.1.0: cannot open shared object file: No such file or directory<a class="headerlink" href="#importerror-libpython3-10-so-1-0-cannot-open-shared-object-file-no-such-file-or-directory" title="Permalink to this heading"></a></h2>
+<p>If you are using <code class="docutils literal notranslate"><span class="pre">conda</span></code> and encounter the following issue:</p>
+<div class="highlight-default notranslate"><div class="highlight"><pre><span></span>Traceback (most recent call last):
+  File &quot;/k2-dev/yangyifan/anaconda3/envs/icefall/lib/python3.10/site-packages/k2-1.23.3.dev20230112+cuda11.6.torch1.13.1-py3.10-linux-x86_64.egg/k2/__init__.py&quot;, line 24, in &lt;module&gt;
+    from _k2 import DeterminizeWeightPushingType
+ImportError: libpython3.10.so.1.0: cannot open shared object file: No such file or directory
+
+During handling of the above exception, another exception occurred:
+
+Traceback (most recent call last):
+  File &quot;/k2-dev/yangyifan/icefall/egs/librispeech/ASR/./pruned_transducer_stateless7_ctc_bs/decode.py&quot;, line 104, in &lt;module&gt;
+    import k2
+  File &quot;/k2-dev/yangyifan/anaconda3/envs/icefall/lib/python3.10/site-packages/k2-1.23.3.dev20230112+cuda11.6.torch1.13.1-py3.10-linux-x86_64.egg/k2/__init__.py&quot;, line 30, in &lt;module&gt;
+    raise ImportError(
+ImportError: libpython3.10.so.1.0: cannot open shared object file: No such file or directory
+Note: If you&#39;re using anaconda and importing k2 on MacOS,
+      you can probably fix this by setting the environment variable:
+  export DYLD_LIBRARY_PATH=$CONDA_PREFIX/lib/python3.10/site-packages:$DYLD_LIBRARY_PATH
+</pre></div>
+</div>
+<p>Please first try to find where <code class="docutils literal notranslate"><span class="pre">libpython3.10.so.1.0</span></code> locates.</p>
+<p>For instance,</p>
+<div class="highlight-bash notranslate"><div class="highlight"><pre><span></span><span class="nb">cd</span><span class="w"> </span><span class="nv">$CONDA_PREFIX</span>/lib
+find<span class="w"> </span>.<span class="w"> </span>-name<span class="w"> </span><span class="s2">&quot;libpython*&quot;</span>
+</pre></div>
+</div>
+<p>If you are able to find it inside <code class="docutils literal notranslate"><span class="pre">$CODNA_PREFIX/lib</span></code>, please set the
+following environment variable:</p>
+<div class="highlight-bash notranslate"><div class="highlight"><pre><span></span><span class="nb">export</span><span class="w"> </span><span class="nv">LD_LIBRARY_PATH</span><span class="o">=</span><span class="nv">$CONDA_PREFIX</span>/lib:<span class="nv">$LD_LIBRARY_PATH</span>
+</pre></div>
+</div>
+</section>
 </section>
 
 

index.html

@@ -97,6 +97,7 @@ speech recognition recipes using <a class="reference external" href="https://git
 <li class="toctree-l1"><a class="reference internal" href="faqs.html">Frequently Asked Questions (FAQs)</a><ul>
 <li class="toctree-l2"><a class="reference internal" href="faqs.html#oserror-libtorch-hip-so-cannot-open-shared-object-file-no-such-file-or-directory">OSError: libtorch_hip.so: cannot open shared object file: no such file or directory</a></li>
 <li class="toctree-l2"><a class="reference internal" href="faqs.html#attributeerror-module-distutils-has-no-attribute-version">AttributeError: module ‘distutils’ has no attribute ‘version’</a></li>
+<li class="toctree-l2"><a class="reference internal" href="faqs.html#importerror-libpython3-10-so-1-0-cannot-open-shared-object-file-no-such-file-or-directory">ImportError: libpython3.10.so.1.0: cannot open shared object file: No such file or directory</a></li>
 </ul>
 </li>
 <li class="toctree-l1"><a class="reference internal" href="model-export/index.html">Model export</a><ul>

recipes/Non-streaming-ASR/aishell/conformer_ctc.html

@@ -332,10 +332,10 @@ $<span class="w"> </span>tensorboard<span class="w"> </span>dev<span class="w">
 <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="id3">
+<div><figure class="align-center" id="id4">
 <a class="reference external image-reference" href="https://tensorboard.dev/experiment/WE1DocDqRRCOSAgmGyClhg/"><img alt="TensorBoard screenshot" src="../../../_images/aishell-conformer-ctc-tensorboard-log.jpg" style="width: 600px;" /></a>
 <figcaption>
-<p><span class="caption-number">Fig. 2 </span><span class="caption-text">TensorBoard screenshot.</span><a class="headerlink" href="#id3" title="Permalink to this image"></a></p>
+<p><span class="caption-number">Fig. 2 </span><span class="caption-text">TensorBoard screenshot.</span><a class="headerlink" href="#id4" title="Permalink to this image"></a></p>
 </figcaption>
 </figure>
 </div></blockquote>

recipes/Non-streaming-ASR/aishell/tdnn_lstm_ctc.html

@@ -328,10 +328,10 @@ $<span class="w"> </span>tensorboard<span class="w"> </span>dev<span class="w">
 <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="id2">
+<div><figure class="align-center" id="id3">
 <a class="reference external image-reference" href="https://tensorboard.dev/experiment/LJI9MWUORLOw3jkdhxwk8A/"><img alt="TensorBoard screenshot" src="../../../_images/aishell-tdnn-lstm-ctc-tensorboard-log.jpg" style="width: 600px;" /></a>
 <figcaption>
-<p><span class="caption-number">Fig. 1 </span><span class="caption-text">TensorBoard screenshot.</span><a class="headerlink" href="#id2" title="Permalink to this image"></a></p>
+<p><span class="caption-number">Fig. 1 </span><span class="caption-text">TensorBoard screenshot.</span><a class="headerlink" href="#id3" title="Permalink to this image"></a></p>
 </figcaption>
 </figure>
 </div></blockquote>

recipes/Non-streaming-ASR/librispeech/conformer_ctc.html

@@ -340,10 +340,10 @@ $<span class="w"> </span>tensorboard<span class="w"> </span>dev<span class="w">
 <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="id4">
+<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-conformer-ctc-tensorboard-log.png" style="width: 600px;" /></a>
 <figcaption>
-<p><span class="caption-number">Fig. 4 </span><span class="caption-text">TensorBoard screenshot.</span><a class="headerlink" href="#id4" title="Permalink to this image"></a></p>
+<p><span class="caption-number">Fig. 4 </span><span class="caption-text">TensorBoard screenshot.</span><a class="headerlink" href="#id6" title="Permalink to this image"></a></p>
 </figcaption>
 </figure>
 </div></blockquote>

recipes/Non-streaming-ASR/librispeech/distillation.html

@@ -100,25 +100,23 @@
              
   <section id="distillation-with-hubert">
 <h1>Distillation with HuBERT<a class="headerlink" href="#distillation-with-hubert" title="Permalink to this heading"></a></h1>
-<p>This totorial shows you how to perform knowledge distillation in <code class="docutils literal notranslate"><span class="pre">icefall</span></code>
+<p>This tutorial shows you how to perform knowledge distillation in <a href="#id7"><span class="problematic" id="id8">`icefall`_</span></a>
 with the <a class="reference external" href="https://www.openslr.org/12">LibriSpeech</a> dataset. The distillation method
 used here is called “Multi Vector Quantization Knowledge Distillation” (MVQ-KD).
 Please have a look at our paper <a class="reference external" href="https://arxiv.org/abs/2211.00508">Predicting Multi-Codebook Vector Quantization Indexes for Knowledge Distillation</a>
 for more details about MVQ-KD.</p>
 <div class="admonition note">
 <p class="admonition-title">Note</p>
-<dl class="simple">
-<dt>This tutorial is based on recipe</dt><dd><p><a class="reference external" href="https://github.com/k2-fsa/icefall/tree/master/egs/librispeech/ASR/pruned_transducer_stateless4">pruned_transducer_stateless4</a>.</p>
-</dd>
-</dl>
-<p>Currently, we only implement MVQ-KD in this recipe. However, MVQ-KD is theoretically applicable to all recipes
+<p>This tutorial is based on recipe
+<a class="reference external" href="https://github.com/k2-fsa/icefall/tree/master/egs/librispeech/ASR/pruned_transducer_stateless4">pruned_transducer_stateless4</a>.
+Currently, we only implement MVQ-KD in this recipe. However, MVQ-KD is theoretically applicable to all recipes
 with only minor changes needed. Feel free to try out MVQ-KD in different recipes. If you
 encounter any problems, please open an issue here <a class="reference external" href="https://github.com/k2-fsa/icefall/issues">icefall</a>.</p>
 </div>
 <div class="admonition note">
 <p class="admonition-title">Note</p>
 <p>We assume you have read the page <a class="reference internal" href="../../../installation/index.html#install-icefall"><span class="std std-ref">Installation</span></a> and have setup
-the environment for <code class="docutils literal notranslate"><span class="pre">icefall</span></code>.</p>
+the environment for <a href="#id9"><span class="problematic" id="id10">`icefall`_</span></a>.</p>
 </div>
 <div class="admonition hint">
 <p class="admonition-title">Hint</p>
@@ -126,12 +124,12 @@ the environment for <code class="docutils literal notranslate"><span class="pre"
 </div>
 <section id="data-preparation">
 <h2>Data preparation<a class="headerlink" href="#data-preparation" title="Permalink to this heading"></a></h2>
-<p>We first prepare necessary training data for <code class="docutils literal notranslate"><span class="pre">LibriSpeech</span></code>.
-This is the same as in <a class="reference external" href="./pruned_transducer_stateless.rst">Pruned_transducer_statelessX</a>.</p>
+<p>We first prepare necessary training data for <a class="reference external" href="https://www.openslr.org/12">LibriSpeech</a>.
+This is the same as in <a class="reference internal" href="pruned_transducer_stateless.html#non-streaming-librispeech-pruned-transducer-stateless"><span class="std std-ref">Pruned transducer statelessX</span></a>.</p>
 <div class="admonition hint">
 <p class="admonition-title">Hint</p>
 <p>The data preparation is the same as other recipes on LibriSpeech dataset,
-if you have finished this step, you can skip to <code class="docutils literal notranslate"><span class="pre">Codebook</span> <span class="pre">index</span> <span class="pre">preparation</span></code> directly.</p>
+if you have finished this step, you can skip to <a class="reference internal" href="#codebook-index-preparation"><span class="std std-ref">Codebook index preparation</span></a> directly.</p>
 </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>./prepare.sh
@@ -180,16 +178,16 @@ the following YouTube channel by <a class="reference external" href="https://www
 <iframe allowfullscreen="true" src="https://www.youtube.com/embed/ofEIoJL-mGM" style="border: 0; height: 345px; width: 560px">
 </iframe></div></section>
 <section id="codebook-index-preparation">
-<h2>Codebook index preparation<a class="headerlink" href="#codebook-index-preparation" title="Permalink to this heading"></a></h2>
+<span id="id1"></span><h2>Codebook index preparation<a class="headerlink" href="#codebook-index-preparation" title="Permalink to this heading"></a></h2>
 <p>Here, we prepare necessary data for MVQ-KD. This requires the generation
 of codebook indexes (please read our <a class="reference external" href="https://arxiv.org/abs/2211.00508">paper</a>.
 if you are interested in details). In this tutorial, we use the pre-computed
 codebook indexes for convenience. The only thing you need to do is to
-run <code class="docutils literal notranslate"><span class="pre">./distillation_with_hubert.sh</span></code>.</p>
+run <a class="reference external" href="https://github.com/k2-fsa/icefall/blob/master/egs/librispeech/ASR/distillation_with_hubert.sh">./distillation_with_hubert.sh</a>.</p>
 <div class="admonition note">
 <p class="admonition-title">Note</p>
 <p>There are 5 stages in total, the first and second stage will be automatically skipped
-when choosing to downloaded codebook indexes prepared by <a class="reference external" href="https://github.com/k2-fsa/icefall/issues">icefall</a>.
+when choosing to downloaded codebook indexes prepared by <a href="#id11"><span class="problematic" id="id12">`icefall`_</span></a>.
 Of course, you can extract and compute the codebook indexes by yourself. This
 will require you downloading a HuBERT-XL model and it can take a while for
 the extraction of codebook indexes.</p>
@@ -208,7 +206,7 @@ $<span class="w"> </span>./distillation_with_hubert.sh<span class="w"> </span>--
 $<span class="w"> </span>./distillation_with_hubert.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">4</span><span class="w"> </span><span class="c1"># run from stage 2 to stage 5</span>
 </pre></div>
 </div>
-<p>Here are a few options in <code class="docutils literal notranslate"><span class="pre">./distillation_with_hubert.sh</span></code>
+<p>Here are a few options in <a class="reference external" href="https://github.com/k2-fsa/icefall/blob/master/egs/librispeech/ASR/distillation_with_hubert.sh">./distillation_with_hubert.sh</a>
 you need to know before you proceed.</p>
 <ul class="simple">
 <li><p><code class="docutils literal notranslate"><span class="pre">--full_libri</span></code> If True, use full 960h data. Otherwise only <code class="docutils literal notranslate"><span class="pre">train-clean-100</span></code> will be used</p></li>
@@ -225,10 +223,10 @@ and prepares MVQ-augmented training manifests.</p>
 </div>
 <p>Please see the
 following screenshot for the output of an example execution.</p>
-<figure class="align-center" id="id3">
+<figure class="align-center" id="id5">
 <a class="reference internal image-reference" href="../../../_images/distillation_codebook.png"><img alt="Downloading codebook indexes and preparing training manifest." src="../../../_images/distillation_codebook.png" style="width: 800px;" /></a>
 <figcaption>
-<p><span class="caption-number">Fig. 6 </span><span class="caption-text">Downloading codebook indexes and preparing training manifest.</span><a class="headerlink" href="#id3" title="Permalink to this image"></a></p>
+<p><span class="caption-number">Fig. 6 </span><span class="caption-text">Downloading codebook indexes and preparing training manifest.</span><a class="headerlink" href="#id5" title="Permalink to this image"></a></p>
 </figcaption>
 </figure>
 <div class="admonition hint">
@@ -239,11 +237,11 @@ with 8 codebooks. If you want to try other configurations, please
 set <code class="docutils literal notranslate"><span class="pre">use_extracted_codebook=False</span></code> and set <code class="docutils literal notranslate"><span class="pre">embedding_layer</span></code> and
 <code class="docutils literal notranslate"><span class="pre">num_codebooks</span></code> by yourself.</p>
 </div>
-<p>Now, you should see the following files under the direcory <code class="docutils literal notranslate"><span class="pre">./data/vq_fbank_layer36_cb8</span></code>.</p>
-<figure class="align-center" id="id4">
+<p>Now, you should see the following files under the directory <code class="docutils literal notranslate"><span class="pre">./data/vq_fbank_layer36_cb8</span></code>.</p>
+<figure class="align-center" id="id6">
 <a class="reference internal image-reference" href="../../../_images/distillation_directory.png"><img alt="MVQ-augmented training manifests" src="../../../_images/distillation_directory.png" style="width: 800px;" /></a>
 <figcaption>
-<p><span class="caption-number">Fig. 7 </span><span class="caption-text">MVQ-augmented training manifests.</span><a class="headerlink" href="#id4" title="Permalink to this image"></a></p>
+<p><span class="caption-number">Fig. 7 </span><span class="caption-text">MVQ-augmented training manifests.</span><a class="headerlink" href="#id6" title="Permalink to this image"></a></p>
 </figcaption>
 </figure>
 <p>Whola! You are ready to perform knowledge distillation training now!</p>

recipes/Non-streaming-ASR/librispeech/pruned_transducer_stateless.html

@@ -99,7 +99,7 @@
            <div itemprop="articleBody">
              
   <section id="pruned-transducer-statelessx">
-<h1>Pruned transducer statelessX<a class="headerlink" href="#pruned-transducer-statelessx" title="Permalink to this heading"></a></h1>
+<span id="non-streaming-librispeech-pruned-transducer-stateless"></span><h1>Pruned transducer statelessX<a class="headerlink" href="#pruned-transducer-statelessx" title="Permalink to this heading"></a></h1>
 <p>This tutorial shows you how to run a conformer transducer model
 with the <a class="reference external" href="https://www.openslr.org/12">LibriSpeech</a> dataset.</p>
 <div class="admonition note">
@@ -378,10 +378,10 @@ $<span class="w"> </span>tensorboard<span class="w"> </span>dev<span class="w">
 <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="id7">
+<div><figure class="align-center" id="id9">
 <a class="reference external image-reference" href="https://tensorboard.dev/experiment/QOGSPBgsR8KzcRMmie9JGw/"><img alt="TensorBoard screenshot" src="../../../_images/librispeech-pruned-transducer-tensorboard-log.jpg" style="width: 600px;" /></a>
 <figcaption>
-<p><span class="caption-number">Fig. 5 </span><span class="caption-text">TensorBoard screenshot.</span><a class="headerlink" href="#id7" title="Permalink to this image"></a></p>
+<p><span class="caption-number">Fig. 5 </span><span class="caption-text">TensorBoard screenshot.</span><a class="headerlink" href="#id9" title="Permalink to this image"></a></p>
 </figcaption>
 </figure>
 </div></blockquote>

recipes/Streaming-ASR/librispeech/lstm_pruned_stateless_transducer.html

@@ -377,10 +377,10 @@ $<span class="w"> </span>tensorboard<span class="w"> </span>dev<span class="w">
 <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="id3">
+<div><figure class="align-center" id="id5">
 <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="#id3" title="Permalink to this image"></a></p>
+<p><span class="caption-number">Fig. 10 </span><span class="caption-text">TensorBoard screenshot.</span><a class="headerlink" href="#id5" title="Permalink to this image"></a></p>
 </figcaption>
 </figure>
 </div></blockquote>

recipes/Streaming-ASR/librispeech/pruned_transducer_stateless.html

@@ -397,10 +397,10 @@ $<span class="w"> </span>tensorboard<span class="w"> </span>dev<span class="w">
 <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="id7">
+<div><figure class="align-center" id="id10">
 <a class="reference external image-reference" href="https://tensorboard.dev/experiment/97VKXf80Ru61CnP2ALWZZg/"><img alt="TensorBoard screenshot" src="../../../_images/streaming-librispeech-pruned-transducer-tensorboard-log.jpg" style="width: 600px;" /></a>
 <figcaption>
-<p><span class="caption-number">Fig. 9 </span><span class="caption-text">TensorBoard screenshot.</span><a class="headerlink" href="#id7" title="Permalink to this image"></a></p>
+<p><span class="caption-number">Fig. 9 </span><span class="caption-text">TensorBoard screenshot.</span><a class="headerlink" href="#id10" title="Permalink to this image"></a></p>
 </figcaption>
 </figure>
 </div></blockquote>