Issues
- 1
For Gammatone filters
#72 opened by WangHelin1997 - 0
Archive the repo
#71 opened by keunwoochoi - 1
Displaying Spectrograms
#70 opened by kamalesh0406 - 1
we need `dtype=torch.get_default_dtype()`
#52 opened by keunwoochoi - 0
Loading Datasets
#69 opened by kamalesh0406 - 2
_ModuleNoStateBuffers
#68 opened by vgoklani - 35
conversation: fast, general audio read
#31 opened by drscotthawley - 11
Merging plan to torch/audio - Phase 1 and 2
#61 opened by keunwoochoi - 8
Signal resampling, sinc interpolation
#40 opened by ksanjeevan - 4
Standardizing audio datasets
#67 opened by scarecrow1123 - 24
ISTFT
#27 opened by keunwoochoi - 11
Downmix - api design
#54 opened by keunwoochoi - 31
- 23
chunking, batch creation
#29 opened by nkundiushuti - 2
Waveform Augmentation
#60 opened by faroit - 6
- 2
File structure
#47 opened by keunwoochoi - 10
Spectrogram Augmentation
#44 opened by ksanjeevan - 11
HTK and Slaney
#24 opened by VinodS7 - 14
Shapes, shapes, shapes
#2 opened by keunwoochoi - 9
unittest vs pytest (again)
#39 opened by keunwoochoi - 4
Python version
#41 opened by keunwoochoi - 7
Proposal on the way we work
#37 opened by keunwoochoi - 7
Functional interface
#35 opened by f0k - 2
Libtorch support?
#23 opened by dhpollack - 4
Place for general discussion?
#18 opened by f0k - 6
harmonic-percussive source separation
#25 opened by keunwoochoi - 2
Spectrogram code review
#22 opened by f0k - 4
API: Composition vs. Inheritance
#20 opened by f0k - 3
Parameter vs. buffer
#19 opened by f0k - 6
SpecAugment
#38 opened by keunwoochoi - 13
How to make contributions?
#16 opened by dansuh17 - 3
- 5
Inverse operations, wiener filter, softmask
#5 opened by faroit - 2
Names, names, names
#1 opened by keunwoochoi - 16
Which layers/operations to implement?
#3 opened by keunwoochoi - 3
Explain MaskConv2d
#4 opened by faroit - 1
PEP8
#6 opened by keunwoochoi - 1
- 32
Spectrogram Power/Magnitude
#7 opened by faroit