Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Embed audio samples in generated tutorials #1985

Merged
merged 2 commits into from
Nov 5, 2021
Merged

Embed audio samples in generated tutorials #1985

Show file tree
Hide file tree
Changes from 1 commit
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
7315e9e
Embed audio samples in generated tutorials
mthrok Nov 5, 2021
3616c10
Tweak a bit
mthrok Nov 5, 2021
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
6 changes: 3 additions & 3 deletions examples/gallery/tts/tacotron2_pipeline_tutorial.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -270,7 +270,7 @@ def text_to_sequence(text):
ax2.plot(waveforms[0].cpu().detach())

torchaudio.save("output_wavernn.wav", waveforms[0:1].cpu(), sample_rate=vocoder.sample_rate)
IPython.display.display(IPython.display.Audio("output_wavernn.wav"))
IPython.display.Audio("output_wavernn.wav")


######################################################################
Expand Down Expand Up @@ -299,7 +299,7 @@ def text_to_sequence(text):
ax2.plot(waveforms[0].cpu().detach())

torchaudio.save("output_griffinlim.wav", waveforms[0:1].cpu(), sample_rate=vocoder.sample_rate)
IPython.display.display(IPython.display.Audio("output_griffinlim.wav"))
IPython.display.Audio("output_griffinlim.wav")


######################################################################
Expand Down Expand Up @@ -330,4 +330,4 @@ def text_to_sequence(text):
ax2.plot(waveforms[0].cpu().detach())

torchaudio.save("output_waveglow.wav", waveforms[0:1].cpu(), sample_rate=22050)
IPython.display.display(IPython.display.Audio("output_waveglow.wav"))
IPython.display.Audio("output_waveglow.wav")
71 changes: 62 additions & 9 deletions examples/gallery/wav2vec2/forced_alignment_tutorial.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -56,8 +56,8 @@
print(torchaudio.__version__)
print(device)

SPEECH_URL = 'https://download.pytorch.org/torchaudio/test-assets/Lab41-SRI-VOiCES-src-sp0307-ch127535-sg0042.flac'
SPEECH_FILE = 'speech.flac'
SPEECH_URL = 'https://download.pytorch.org/torchaudio/tutorial-assets/Lab41-SRI-VOiCES-src-sp0307-ch127535-sg0042.wav'
SPEECH_FILE = 'speech.wav'

if not os.path.exists(SPEECH_FILE):
with open(SPEECH_FILE, 'wb') as file:
Expand Down Expand Up @@ -422,18 +422,71 @@ def plot_alignments(trellis, segments, word_segments, waveform):
plot_alignments(trellis, segments, word_segments, waveform[0],)
plt.show()

# Generate the audio for each segment
print(transcript)
IPython.display.display(IPython.display.Audio(SPEECH_FILE))
ratio = waveform.size(1) / (trellis.size(0) - 1)
for i, word in enumerate(word_segments):
# A trick to embed the resulting audio to the generated file.
# `IPython.display.Audio` has to be the last call in a cell,
# and there should be only one call.
def _show(i):
ratio = waveform.size(1) / (trellis.size(0) - 1)
word = word_segments[i]
x0 = int(ratio * word.start)
x1 = int(ratio * word.end)
filename = f"{i}_{word.label}.wav"
torchaudio.save(filename, waveform[:, x0:x1], bundle.sample_rate)
print(f"{word.label}: {x0 / bundle.sample_rate:.3f} - {x1 / bundle.sample_rate:.3f}")
IPython.display.display(IPython.display.Audio(filename))
print(f"{word.label} ({word.score:.2f}): {x0 / bundle.sample_rate:.3f} - {x1 / bundle.sample_rate:.3f} sec")
return filename

######################################################################
#

# Generate the audio for each segment
print(transcript)
IPython.display.Audio(SPEECH_FILE)


######################################################################
#

IPython.display.Audio(_show(0))

######################################################################
#

IPython.display.Audio(_show(1))

######################################################################
#

IPython.display.Audio(_show(2))

######################################################################
#

IPython.display.Audio(_show(3))

######################################################################
#

IPython.display.Audio(_show(4))

######################################################################
#

IPython.display.Audio(_show(5))

######################################################################
#

IPython.display.Audio(_show(6))

######################################################################
#

IPython.display.Audio(_show(7))

######################################################################
#

IPython.display.Audio(_show(8))

######################################################################
# Conclusion
Expand Down
4 changes: 2 additions & 2 deletions examples/gallery/wav2vec2/speech_recognition_pipeline_tutorial.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -120,7 +120,7 @@
# Creative Commos BY 4.0.
#

IPython.display.display(IPython.display.Audio(SPEECH_FILE))
IPython.display.Audio(SPEECH_FILE)


######################################################################
Expand Down Expand Up @@ -273,7 +273,7 @@ def forward(self, emission: torch.Tensor) -> str:
#

print(transcript)
IPython.display.display(IPython.display.Audio(SPEECH_FILE))
IPython.display.Audio(SPEECH_FILE)


######################################################################
Expand Down