Hacker News Reader

Hey, saw your comments a couple of weeks ago on the wavenetVA repo, this is looking great! Will try training spring reverb and analog tape, those have been pretty hard to model with DSP.

Also, what do you think about diffwave? Only seen speech examples so far but seems an order of magnitude faster than wavenet.

https://github.com/lmnt-com/diffwave

View on HN

Nice, I’ll have to look into diffwave, have not heard of that. You may have difficulty training on reverb effects due to the nature of the WaveNet model. It works well for distortion, but for effects that extend past around 50 milliseconds like reverb or delay, it might not be able to capture it properly.

Reply on news.ycombinator.com