Tweak tutorials (#2733)

Summary:
* Port downstream change https://github.com/pytorch/tutorials/pull/2060
* Fix inter-tutorial links and references

Pull Request resolved: https://github.com/pytorch/audio/pull/2733

Reviewed By: hwangjeff

Differential Revision: D40086902

Pulled By: hwangjeff

fbshipit-source-id: 00b04c6a1b68fb9fadd52b610b26ecaab15d52d8

docs/source/conf.py

@@ -123,6 +123,7 @@ sphinx_gallery_conf = {
     ],
     **_get_pattern(),
     "backreferences_dir": "gen_modules/backreferences",
+    "promote_jupyter_magic": True,
     "first_notebook_cell": None,
     "doc_module": ("torchaudio",),
 }

examples/tutorials/device_asr.py

@@ -36,7 +36,7 @@ on laptop.
 #
 # For the basic usage of the streaming API and Emformer RNN-T
 # please refer to
-# `Media Stream API tutorial <./streaming_api_tutorial.html>`__ and
+# `StreamReader Basic Usage <./streamreader_basic_tutorial.html>`__ and
 # `Online ASR with Emformer RNN-T <./online_asr_tutorial.html>`__.
 #
 

examples/tutorials/online_asr_tutorial.py

@@ -115,7 +115,7 @@ print(f"Right context: {context_length} frames ({context_length / sample_rate} s
 # Next, we configure the input audio stream using :py:class:`torchaudio.io.StreamReader`.
 #
 # For the detail of this API, please refer to the
-# `Media Stream API tutorial <./streaming_api_tutorial.html>`__.
+# `StreamReader Basic Usage <./streamreader_basic_tutorial.html>`__.
 #
 
 ######################################################################

examples/tutorials/streamreader_advanced_tutorial.py

@@ -3,7 +3,7 @@ StreamReader Advanced Usages
 ============================
 
 This tutorial is the continuation of
-`StreamReader Basic Usages <./streaming_api_tutorial.html>`__.
+`StreamReader Basic Usages <./streamreader_basic_tutorial.html>`__.
 
 This shows how to use :py:class:`~torchaudio.io.StreamReader` for
 

examples/tutorials/streamreader_basic_tutorial.py

@@ -105,7 +105,7 @@ VIDEO_URL = f"{base_url}/stream-api/NASAs_Most_Scientifically_Complex_Space_Obse
 #
 # The following section covers how to open common media formats.
 # For the other streams, please refer to the
-# `Media Stream API - Pt.2 <./streaming_api2_tutorial.html>`__.
+# `StreamReader Advanced Usage <./streamreader_advanced_tutorial.html>`__.
 #
 # .. note::
 #

examples/tutorials/tacotron2_pipeline_tutorial.py

@@ -35,9 +35,8 @@ import matplotlib.pyplot as plt
 #    The last step is converting the spectrogram into the waveform. The
 #    process to generate speech from spectrogram is also called Vocoder.
 #    In this tutorial, three different vocoders are used,
-#    `WaveRNN <https://pytorch.org/audio/stable/models/wavernn.html>`__,
-#    `Griffin-Lim <https://pytorch.org/audio/stable/transforms.html#griffinlim>`__,
-#    and
+#    :py:class:`~torchaudio.models.WaveRNN`,
+#    :py:class:`~torchaudio.transforms.GriffinLim`, and
 #    `Nvidia's WaveGlow <https://pytorch.org/hub/nvidia_deeplearningexamples_tacotron2/>`__.
 #
 #
@@ -57,8 +56,11 @@ import matplotlib.pyplot as plt
 # encoding.
 #
 
-# When running this example in notebook, install DeepPhonemizer
-# !pip3 install deep_phonemizer
+# %%
+#  .. code-block:: bash
+#
+#      %%bash
+#      pip3 install deep_phonemizer
 
 import torch
 import torchaudio
@@ -216,7 +218,7 @@ with torch.inference_mode():
     spec, _, _ = tacotron2.infer(processed, lengths)
 
 
-plt.imshow(spec[0].cpu().detach())
+_ = plt.imshow(spec[0].cpu().detach())
 
 
 ######################################################################