Issues: pytorch/audio
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.
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
Author
Label
Projects
Milestones
Assignee
Sort
Issues list
List of feature requests received so far for StreamReader/Writer
module: IO
triaged
#3139
opened Mar 2, 2023 by
mthrok
2 tasks done
torchaudio.transforms.SpectralCentroid supports only real valued input
triaged
#3114
opened Feb 28, 2023 by
rgt-yncrea
Documentation error about torchaudio.transforms.Spectrogram
help wanted
triaged
#3101
opened Feb 26, 2023 by
cai525
Wav2vec2.0 Pretrained model gives different emission results for different batch size input.
improvement
triaged
#3094
opened Feb 23, 2023 by
yuekaizhang
CMake cannot fine Python.h when building from source
triaged
#3069
opened Feb 16, 2023 by
singingwolfboy
Add filter and filter_complex to StreamWriter
module: IO
triaged
#3063
opened Feb 15, 2023 by
maysteinfeld
Use non-persistent buffers
good first issue
help wanted
triaged
#3059
opened Feb 14, 2023 by
Thylane
Why cpu and gpu have different results when logit_length and target_length has some 1?
triaged
#3048
opened Feb 9, 2023 by
bleedingfight
torchaudio.load returns 0 frames from ogg files when provided with random offsets
needs triage
#3012
opened Jan 25, 2023 by
draguve
InverseSpectrogram output is shorter than Spectrogram input for same kwargs
triaged
#3003
opened Jan 23, 2023 by
drscotthawley
Add ctc beam search decoder using cuda implementation
triaged
#2957
opened Jan 5, 2023 by
yuekaizhang
Previous Next
ProTip!
Add no:assignee to see everything that’s not assigned.

