torch-audiomentations

torch-audiomentations copied to clipboard

Change the spectrum. Boost some frequencies, maybe attenuate some frequencies.

iver56

In pyannote.audio we have a a set of functions that run before commiting. This is through the pre-commit git hook. It makes code styling more consistent, checks for missing imports...

mogwai

Originally [posted](https://github.com/asteroid-team/torch-audiomentations/pull/51#issuecomment-736407087) by @iver56

mogwai

Implement resample transform

9

https://github.com/adefossez/julius

iver56

Implement temporal masking

2

@nicofarr

iver56

@nicofarr torch-audiomentations works on tensors with shapes like (batch_size, samples) or (batch_size, channels, samples) How do you propose CutMix would work when replacing some of the audio in an audio...

iver56

iver56

https://github.com/asteroid-team/torch-audiomentations/pull/32/files/3d5d9293bb31716e8cbf21e064a85d879940f835#diff-f8aff5239b5132abfaddcbaa25a0342ec801e5f75e0b82f27757169fa5a82c68

iver56

Some things, like mp3 compression, are not easy to implement in pytorch, so we have to rely on other libraries like `audiomentations` for that. Here's an example of what I...

iver56

For multi-GPU training, users might use `DataParallel` and `DistributedDataParallel`. And the augmentations should probably follow that as well, to avoid copying parameters from one device to another (and loosing more...

mpariente