Sorry for the delay, I just saw this. The audio module isn’t as mature as the rest of v2 so a walkthrough wouldn’t be that useful, but we have a lot of audio resources if you’re looking to get started. See the Deep Learning With Audio Thread and post any questions or share what you’re working on/interested in. Or for now try out the fastai v1 audio library (external).
We also have a telegram chat for audio ML, if that interests you DM me your telegram details and I’ll get you in.