Skip to content

Option to use speech-optimized tempo effect in from time_stretch() #89

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

Open
babua wants to merge 2 commits into
base: ps/pinwavesurfer
Choose a base branch
from
Open

Option to use speech-optimized tempo effect in from time_stretch() #89

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
ed434ed
Option to use speech-optimized SoX tempo effect called from time_stre…
babua Jul 12, 2023
f465513
added test case for previous default
babua Jul 21, 2023
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
5 changes: 4 additions & 1 deletion audiotools/core/effects.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -276,7 +276,7 @@ def pitch_shift(self, n_semitones: int, quick: bool = True):
self.audio_data = self._to_3d(waveform)
return self.to(device)

def time_stretch(self, factor: float, quick: bool = True):
def time_stretch(self, factor: float, quick: bool = True, speech: bool = True):
"""Time stretch the audio signal.

Parameters
Expand All @@ -300,6 +300,9 @@ def time_stretch(self, factor: float, quick: bool = True):
if quick:
effects[0].insert(1, "-q")

if speech:
effects[0].insert(1, "-s")

waveform = self._to_2d().cpu()
waveform, sample_rate = torchaudio.sox_effects.apply_effects_tensor(
waveform, self.sample_rate, effects, channels_first=True
Expand Down
7 changes: 7 additions & 0 deletions tests/core/test_effects.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -178,6 +178,13 @@ def test_time_stretch():

batched = spk_batch.deepcopy().time_stretch(0.8)

#non-default case
single = spk.deepcopy().time_stretch(0.8, speech=False)

spk_batch = AudioSignal.batch([spk.deepcopy() for _ in range(batch_size)])

batched = spk_batch.deepcopy().time_stretch(0.8, speech=False)

assert np.allclose(batched[0].audio_data, single[0].audio_data)


Expand Down