Data Augmentation for Audiofiles

[Kla (Klaudjo Aliaj)]

Hello everyone,

I’m trying to make a data augmentation for my audio DNN but unfortunately I’m not finding the right solution. I have found only torch.nn.Transformer but it seems to be only for photos. Can someone please help me?

[smth]

have a look at TorchAudio, which has a lot of audio preprocessing facilities:

• https://github.com/pytorch/audio
• https://pytorch.org/audio/

[Kla (Klaudjo Aliaj)]

Thank you