Cherry-pick #2767 to release/0.13 (#2805)

docs/source/_static/css/custom.css

@@ -26,3 +26,12 @@ article.pytorch-article .sphx-glr-thumbnails .sphx-glr-thumbcontainer {
 article.pytorch-article div.section div.wy-table-responsive tbody td {
     width: 50%;
 }
+/* For customcarditem*/
+article.pytorch-article div.tutorials-card div.card-body code {
+    color:#d14;
+    padding: 2px 4px;
+    border-radius: 6px;
+    border-top: none;
+    border-bottom: none;
+    background-color: #AFB8C133;
+}

docs/source/_templates/layout.html

@@ -55,7 +55,7 @@
 
 {%- block footer %}
     <script type="text/javascript">
-    var collapsedSections = []
+    var collapsedSections = ['API Tutorials', 'Pipeline Tutorials']
     </script>
     {{ super() }}
     <script type="text/javascript">

docs/source/conf.py

@@ -347,7 +347,7 @@ def setup(app):
     app.connect("autodoc-process-docstring", inject_minigalleries)
 
 
-from custom_directives import SupportedDevices, SupportedProperties
+from custom_directives import CustomCardEnd, CustomCardItem, CustomCardStart, SupportedDevices, SupportedProperties
 
 # Register custom directives
 
@@ -355,3 +355,6 @@ from docutils.parsers import rst
 
 rst.directives.register_directive("devices", SupportedDevices)
 rst.directives.register_directive("properties", SupportedProperties)
+rst.directives.register_directive("customcardstart", CustomCardStart)
+rst.directives.register_directive("customcarditem", CustomCardItem)
+rst.directives.register_directive("customcardend", CustomCardEnd)

docs/source/custom_directives.py

@@ -6,7 +6,9 @@ from urllib.parse import quote, urlencode
 
 import requests
 from docutils import nodes
+from docutils.parsers.rst import Directive, directives
 from docutils.parsers.rst.directives.images import Image
+from docutils.statemachine import StringList
 from sphinx.util.docutils import SphinxDirective
 
 
@@ -125,3 +127,101 @@ class SupportedProperties(BaseShield):
             "style": "flat-square",
         }
         return super().run(params, alt, "properties")
+
+
+_CARDLIST_START = """
+.. raw:: html
+
+   <div id="tutorial-cards-container">
+     <nav class="navbar navbar-expand-lg navbar-light tutorials-nav col-12">
+       <div class="tutorial-tags-container">
+         <div id="dropdown-filter-tags">
+           <div class="tutorial-filter-menu">
+             <div class="tutorial-filter filter-btn all-tag-selected" data-tag="all">All</div>
+           </div>
+         </div>
+       </div>
+     </nav>
+
+     <hr class="tutorials-hr">
+
+     <div class="row">
+       <div id="tutorial-cards">
+         <div class="list">
+"""
+
+_CARD_TEMPLATE = """
+.. raw:: html
+
+   <div class="col-md-12 tutorials-card-container" data-tags={tags}>
+     <div class="card tutorials-card">
+       <a href="{link}">
+         <div class="card-body">
+           <div class="card-title-container">
+             <h4>{header}</h4>
+           </div>
+           <p>Topics: <span class="tags">{tags}</span></p>
+           <p class="card-summary">{card_description}</p>
+           <div class="tutorials-image">{image}</div>
+         </div>
+       </a>
+     </div>
+   </div>
+"""
+
+_CARDLIST_END = """
+.. raw:: html
+
+         </div>
+         <div class="pagination d-flex justify-content-center"></div>
+       </div>
+     </div>
+   </div>
+"""
+
+
+class CustomCardStart(Directive):
+    def run(self):
+        para = nodes.paragraph()
+        self.state.nested_parse(StringList(_CARDLIST_START.split("\n")), self.content_offset, para)
+        return [para]
+
+
+class CustomCardItem(Directive):
+    option_spec = {
+        "header": directives.unchanged,
+        "image": directives.unchanged,
+        "link": directives.unchanged,
+        "card_description": directives.unchanged,
+        "tags": directives.unchanged,
+    }
+
+    def run(self):
+        for key in ["header", "card_description", "link"]:
+            if key not in self.options:
+                raise ValueError(f"Key: `{key}` is missing")
+
+        header = self.options["header"]
+        link = self.options["link"]
+        card_description = self.options["card_description"]
+        tags = self.options.get("tags", "")
+
+        if "image" in self.options:
+            image = "<img src='" + self.options["image"] + "'>"
+        else:
+            image = "_static/img/thumbnails/default.png"
+
+        card_rst = _CARD_TEMPLATE.format(
+            header=header, image=image, link=link, card_description=card_description, tags=tags
+        )
+        card_list = StringList(card_rst.split("\n"))
+        card = nodes.paragraph()
+        self.state.nested_parse(card_list, self.content_offset, card)
+        return [card]
+
+
+class CustomCardEnd(Directive):
+    def run(self):
+        para = nodes.paragraph()
+        self.state.nested_parse(StringList(_CARDLIST_END.split("\n")), self.content_offset, para)
+        return [para]

docs/source/feature_classifications.rst

+Feature Classifications
+=======================
+
+Features described in this documentation are classified by release status:
+
+*Stable:*  These features will be maintained long-term and there should generally
+be no major performance limitations or gaps in documentation.
+We also expect to maintain backwards compatibility (although
+breaking changes can happen and notice will be given one release ahead
+of time).
+
+*Beta:*  Features are tagged as Beta because the API may change based on
+user feedback, because the performance needs to improve, or because
+coverage across operators is not yet complete. For Beta features, we are
+committing to seeing the feature through to the Stable classification.
+We are not, however, committing to backwards compatibility.
+
+*Prototype:*  These features are typically not available as part of
+binary distributions like PyPI or Conda, except sometimes behind run-time
+flags, and are at an early stage for feedback and testing.

docs/source/index.rst

@@ -5,39 +5,57 @@ Torchaudio is a library for audio and signal processing with PyTorch.
 It provides I/O, signal and data processing functions, datasets,
 model implementations and application components.
 
-Features described in this documentation are classified by release status:
-
-  *Stable:*  These features will be maintained long-term and there should generally
-  be no major performance limitations or gaps in documentation.
-  We also expect to maintain backwards compatibility (although
-  breaking changes can happen and notice will be given one release ahead
-  of time).
-
-  *Beta:*  Features are tagged as Beta because the API may change based on
-  user feedback, because the performance needs to improve, or because
-  coverage across operators is not yet complete. For Beta features, we are
-  committing to seeing the feature through to the Stable classification.
-  We are not, however, committing to backwards compatibility.
-
-  *Prototype:*  These features are typically not available as part of
-  binary distributions like PyPI or Conda, except sometimes behind run-time
-  flags, and are at an early stage for feedback and testing.
+..
+   Generate Table Of Contents (left navigation bar)
+   NOTE: If you are adding tutorials, add entries to toctree and customcarditem below
 
 .. toctree::
    :maxdepth: 1
-   :hidden:
    :caption: Torchaudio Documentation
+   :hidden:
 
    Index <self>
    supported_features
+   feature_classifications
    references
 
-API References
---------------
+.. toctree::
+   :maxdepth: 1
+   :caption: API Tutorials
+   :hidden:
+
+   tutorials/audio_io_tutorial
+   tutorials/streamreader_basic_tutorial
+   tutorials/streamreader_advanced_tutorial
+   tutorials/streamwriter_basic_tutorial
+   tutorials/streamwriter_advanced
+   hw_acceleration_tutorial
+
+   tutorials/audio_resampling_tutorial
+   tutorials/audio_data_augmentation_tutorial
+   tutorials/audio_feature_extractions_tutorial
+   tutorials/audio_feature_augmentation_tutorial
+
+   tutorials/audio_datasets_tutorial
+
+.. toctree::
+   :maxdepth: 1
+   :caption: Pipeline Tutorials
+   :hidden:
+
+   tutorials/speech_recognition_pipeline_tutorial
+   tutorials/asr_inference_with_ctc_decoder_tutorial
+   tutorials/online_asr_tutorial
+   tutorials/device_asr
+   tutorials/forced_alignment_tutorial
+   tutorials/tacotron2_pipeline_tutorial
+   tutorials/mvdr_tutorial
+   tutorials/hybrid_demucs_tutorial
 
 .. toctree::
    :maxdepth: 1
    :caption: API Reference
+   :hidden:
 
    torchaudio
    io
@@ -53,35 +71,159 @@ API References
    kaldi_io
    utils
 
-Getting Started
----------------
-    
 .. toctree::
    :maxdepth: 1
-   :caption: Getting Started
+   :caption: PyTorch Libraries
+   :hidden:
 
-   tutorials.io
-   tutorials/audio_resampling_tutorial
-   tutorials/audio_data_augmentation_tutorial
-   tutorials/audio_feature_extractions_tutorial
-   tutorials/audio_feature_augmentation_tutorial
-   tutorials/audio_datasets_tutorial
+   PyTorch <https://pytorch.org/docs>
+   torchaudio <https://pytorch.org/audio>
+   torchtext <https://pytorch.org/text>
+   torchvision <https://pytorch.org/vision>
+   TorchElastic <https://pytorch.org/elastic/>
+   TorchServe <https://pytorch.org/serve>
+   PyTorch on XLA Devices <http://pytorch.org/xla/>
 
-Advanced Usages
----------------
+Tutorials
+---------
 
-.. toctree::
-   :maxdepth: 1
-   :caption: Advanced Usages
+.. customcardstart::
+
+.. customcarditem::
+   :header: Loading waveform Tensors from files and saving them
+   :card_description: Learn how to query/load audio files and save waveform tensors to files, using <code>torchaudio.info</code>, <code>torchaudio.load</code> and <code>torchaudio.save</code> functions.
+   :image: https://download.pytorch.org/torchaudio/tutorial-assets/thumbnails/audio_io_tutorial.png
+   :link: tutorials/audio_io_tutorial.html
+   :tags: I/O
+
+.. customcarditem::
+   :header: Streaming media decoding with StreamReader
+   :card_description: Learn how to load audio/video to Tensors using <code>torchaudio.io.StreamReader</code> class.
+   :image: https://download.pytorch.org/torchaudio/tutorial-assets/thumbnails/streamreader_basic_tutorial.png
+   :link: tutorials/streamreader_basic_tutorial.html
+   :tags: I/O,StreamReader
+
+.. customcarditem::
+   :header: Device input, synthetic audio/video, and filtering with StreamReader
+   :card_description: Learn how to load media from hardware devices, generate synthetic audio/video, and apply filters to them with <code>torchaudio.io.StreamReader</code>.
+   :image: https://download.pytorch.org/torchaudio/tutorial-assets/thumbnails/streamreader_advanced_tutorial.gif
+   :link: tutorials/streamreader_advanced_tutorial.html
+   :tags: I/O,StreamReader
+
+.. customcarditem::
+   :header: Streaming media encoding with StreamWriter
+   :card_description: Learn how to save audio/video with <code>torchaudio.io.StreamWriter</code>.
+   :image: https://download.pytorch.org/torchaudio/tutorial-assets/thumbnails/streamwriter_basic_tutorial.gif
+   :link: tutorials/streamwriter_basic_tutorial.html
+   :tags: I/O,StreamWriter
+   
+.. customcarditem::
+   :header: Playing media with StreamWriter
+   :card_description: Learn how to play audio/video with <code>torchaudio.io.StreamWriter</code>.
+   :image: https://download.pytorch.org/torchaudio/tutorial-assets/thumbnails/streamwriter_advanced.gif
+   :link: tutorials/streamwriter_advanced.html
+   :tags: I/O,StreamWriter
+
+.. customcarditem::
+   :header: Hardware accelerated video I/O with NVDEC/NVENC
+   :card_description: Learn how to setup and use HW accelerated video I/O.
+   :image: https://download.pytorch.org/torchaudio/tutorial-assets/thumbnails/hw_acceleration_tutorial.png
+   :link: hw_acceleration_tutorial.html
+   :tags: I/O,StreamReader,StreamWriter
+
+.. customcarditem::
+   :header: Audio resampling with bandlimited sinc interpolation
+   :card_description: Learn how to resample audio tensor with <code>torchaudio.functional.resample</code> and <code>torchaudio.transforms.Resample</code>.
+   :image: https://download.pytorch.org/torchaudio/tutorial-assets/thumbnails/audio_resampling_tutorial.png
+   :link: tutorials/audio_resampling_tutorial.html
+   :tags: Preprocessing
+
+.. customcarditem::
+   :header: Audio data augmentation
+   :card_description: Learn how to use <code>torchaudio.functional</code> and <code>torchaudio.transforms</code> modules to perform data augmentation.
+   :image: https://download.pytorch.org/torchaudio/tutorial-assets/thumbnails/audio_data_augmentation_tutorial.png
+   :link: tutorials/audio_data_augmentation_tutorial.html
+   :tags: Preprocessing
+
+.. customcarditem::
+   :header: Audio feature extraction
+   :card_description: Learn how to use <code>torchaudio.functional</code> and <code>torchaudio.transforms</code> modules to extract features from waveform.
+   :image: https://download.pytorch.org/torchaudio/tutorial-assets/thumbnails/audio_feature_extractions_tutorial.png
+   :link: tutorials/audio_feature_extractions_tutorial.html
+   :tags: Preprocessing
+
+.. customcarditem::
+   :header: Audio feature augmentation
+   :card_description: Learn how to use <code>torchaudio.functional</code> and <code>torchaudio.transforms</code> modules to perform feature augmentation.
+   :image: https://download.pytorch.org/torchaudio/tutorial-assets/thumbnails/audio_feature_augmentation_tutorial.png
+   :link: tutorials/audio_feature_augmentation_tutorial.html
+   :tags: Preprocessing
+
+.. customcarditem::
+   :header: Audio dataset
+   :card_description: Learn how to use <code>torchaudio.datasets</code> module.
+   :image: https://download.pytorch.org/torchaudio/tutorial-assets/thumbnails/audio_datasets_tutorial.png
+   :link: tutorials/audio_datasets_tutorial.html
+   :tags: Dataset
+
+.. customcarditem::
+   :header: AM inference with Wav2Vec2
+   :card_description: Learn how to perform acoustic model inference with Wav2Vec2 (<code>torchaudio.pipelines.Wav2Vec2ASRBundle</code>).
+   :image: https://download.pytorch.org/torchaudio/tutorial-assets/thumbnails/speech_recognition_pipeline_tutorial.png
+   :link: tutorials/speech_recognition_pipeline_tutorial.html
+   :tags: ASR,wav2vec2
+
+.. customcarditem::
+   :header: LM inference with CTC Beam Seach Decoder
+   :card_description: Learn how to perform ASR beam search decoding with lexicon and language model, using <code>torchaudio.models.decoder.ctc_decoder</code>.
+   :image: https://download.pytorch.org/torchaudio/tutorial-assets/thumbnails/asr_inference_with_ctc_decoder_tutorial.png
+   :link: tutorials/asr_inference_with_ctc_decoder_tutorial.html
+   :tags: Pipelines,ASR,wav2vec2,CTC-Decoder
+
+.. customcarditem::
+   :header: Online ASR with Emformer RNN-T
+   :card_description: Learn how to perform online ASR with Emformer RNN-T (<code>torchaudio.pipelines.RNNTBundle</code>) and <code>torchaudio.io.StreamReader</code>.
+   :image: https://download.pytorch.org/torchaudio/tutorial-assets/thumbnails/online_asr_tutorial.gif
+   :link: tutorials/online_asr_tutorial.html
+   :tags: Pipelines,ASR,RNNT,StreamReader
+   
+.. customcarditem::
+   :header: Real-time microphone ASR with Emformer RNN-T
+   :card_description: Learn how to transcribe speech fomr microphone with Emformer RNN-T (<code>torchaudio.pipelines.RNNTBundle</code>) and <code>torchaudio.io.StreamReader</code>.
+   :image: https://download.pytorch.org/torchaudio/tutorial-assets/thumbnails/device_asr.png
+   :link: tutorials/device_asr.html
+   :tags: Pipelines,ASR,RNNT,StreamReader
+
+.. customcarditem::
+   :header: Forced Alignment with Wav2Vec2
+   :card_description: Learn how to align text to speech with Wav2Vec 2 (<code>torchaudio.pipelines.Wav2Vec2ASRBundle</code>).
+   :image: https://download.pytorch.org/torchaudio/tutorial-assets/thumbnails/forced_alignment_tutorial.png
+   :link: tutorials/forced_alignment_tutorial.html
+   :tags: Pipelines,Forced-Alignment,wav2vec2
+
+.. customcarditem::
+   :header: Text-to-Speech with Tacotron2
+   :card_description: Learn how to generate speech from text with Tacotron2 (<code>torchaudio.pipelines.Tacotron2TTSBundle</code>).
+   :image: https://download.pytorch.org/torchaudio/tutorial-assets/thumbnails/tacotron2_pipeline_tutorial.png
+   :link: tutorials/tacotron2_pipeline_tutorial.html
+   :tags: Pipelines,TTS-(Text-to-Speech)
+   
+.. customcarditem::
+   :header: Speech Enhancement with MVDR Beamforming
+   :card_description: Learn how to improve speech quality with MVDR Beamforming.
+   :image: https://download.pytorch.org/torchaudio/tutorial-assets/thumbnails/mvdr_tutorial.png
+   :link: tutorials/mvdr_tutorial.html
+   :tags: Pipelines,Speech-Enhancement
+
+.. customcarditem::
+   :header: Music Source Separation with Hybrid Demucs
+   :card_description: Learn how to perform music source separation with pre-trained Hybrid Demucs (<code>torchaudio.pipelines.SourceSeparationBundle</code>).
+   :image: https://download.pytorch.org/torchaudio/tutorial-assets/thumbnails/hybrid_demucs_tutorial.png
+   :link: tutorials/hybrid_demucs_tutorial.html
+   :tags: Pipelines,Source-Separation
+
+.. customcardend::
 
-   tutorials/speech_recognition_pipeline_tutorial
-   tutorials/online_asr_tutorial
-   tutorials/device_asr
-   tutorials/forced_alignment_tutorial
-   tutorials/tacotron2_pipeline_tutorial
-   tutorials/mvdr_tutorial
-   tutorials/asr_inference_with_ctc_decoder_tutorial
-   tutorials/hybrid_demucs_tutorial
 
 Citing torchaudio
 -----------------
@@ -112,16 +254,3 @@ In BibTeX format:
       journal={arXiv preprint arXiv:2110.15018},
       year={2021}
     }
-
-.. toctree::
-   :maxdepth: 1
-   :caption: PyTorch Libraries
-   :hidden:
-
-   PyTorch <https://pytorch.org/docs>
-   torchaudio <https://pytorch.org/audio>
-   torchtext <https://pytorch.org/text>
-   torchvision <https://pytorch.org/vision>
-   TorchElastic <https://pytorch.org/elastic/>
-   TorchServe <https://pytorch.org/serve>
-   PyTorch on XLA Devices <http://pytorch.org/xla/>

docs/source/tutorials.io.rst

-Media IO
-========
-
-TorchAudio project has started as a simple audio IO library for PyTorch, which are
-:py:func:`torchaudio.info`, :py:func:`torchaudio.load` and :py:func:`torchaudio.save`.
-
-In recent releases, more powerful IO features were added in :py:mod:`torchaudio.io`.
-These features are based on FFmpeg libraries, thus cross-platform and can handle
-wide variety of media formats, including audio and video, coming from many different source.
-
-
-.. toctree::
-   :maxdepth: 1
-   :caption: Media IO Tutorials
-
-   tutorials/audio_io_tutorial
-   tutorials/streamreader_basic_tutorial
-   tutorials/streamreader_advanced_tutorial
-   tutorials/streamwriter_basic_tutorial
-   tutorials/streamwriter_advanced
-   hw_acceleration_tutorial