Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

How to Train a Gen AI Kick Drum Model on Your Old Linux Desktop with 6GB VRAM

zhinit.dev

Post reply on HN
Print view View original

31–40 of 93 posts

Re: How to Train a Gen AI Kick Drum Model on Your Old Linux Desktop with 6GB VRAM

#31

Post by zhinit »

aw123 wrote: post #29
larme wrote: post #25

People who are interested in this application should check synplant[0]. It has a ML technology called "Genopatch" which gives you 2 functionality: 1. you can try to describe a sound with some tags and it will try to generate a sound to capture the feeling of these tags 2.you can feed it with a sound sample and it will try to re-synthesize the sound with its synth engine. Though the end result will usually be just a "…

How far are we from getting a general model that can resynthesize any instrumental audio sound without fiddling with any knobs, so that we can recreate instruments we hear from any song? Seems like it should exist by now?

SUNO is pretty close. It still has some weird things going on with high frequency artifacts and phase between left and right channels but if you aren't listening on a good system (like a phone) most people probably wont notice.

Re: How to Train a Gen AI Kick Drum Model on Your Old Linux Desktop with 6GB VRAM

#32

Post by zhinit »

johndear223 wrote: post #17

Articles like this are why I come back to HN. Interesting technically, kinda novel and fun. Got me thinking about datasets that may be sitting on old HDD, got TBs of old video and audio from projects of past. Blogs like this help point the way.. Now if only I had the time..

Thanks!

Re: How to Train a Gen AI Kick Drum Model on Your Old Linux Desktop with 6GB VRAM

#33

Post by zhinit »

cocodill wrote: post #28

someone needs to take care of the snares

If you are committed the model should work about the same on any type of one shot sample. The code is public and documented so if you have the snare collection and a macbook you could probably point claude/chatgpt at it and it would be able to train on your laptop.

Re: How to Train a Gen AI Kick Drum Model on Your Old Linux Desktop with 6GB VRAM

#34

Post by andai »

zhinit wrote: post #10
pringk02 wrote: post #2

I just wish it had samples! I want to hear it

For sure! I just added a couple

Did you save any of the "failed" results? I'd love to hear what kind of weird sounds it makes out of distribution (e.g. on the keywords it didn't have much data for).

Re: How to Train a Gen AI Kick Drum Model on Your Old Linux Desktop with 6GB VRAM

#35

Post by larme »

aw123 wrote: post #29
larme wrote: post #25

People who are interested in this application should check synplant[0]. It has a ML technology called "Genopatch" which gives you 2 functionality: 1. you can try to describe a sound with some tags and it will try to generate a sound to capture the feeling of these tags 2.you can feed it with a sound sample and it will try to re-synthesize the sound with its synth engine. Though the end result will usually be just a "…

How far are we from getting a general model that can resynthesize any instrumental audio sound without fiddling with any knobs, so that we can recreate instruments we hear from any song? Seems like it should exist by now?

For me creating the exact sound is not very interesting from sound designing perspective. You can always sample the real instrument.

Like physical modeling synthesis, the interesting part is to compress the sound to some parameters that you can tweak and generate new sounds

Another approach is VAE, which also you give your some latent embedding, you can tweak the embedding to generate new sound. However the meaning of this embedding is not explicit.

Re: How to Train a Gen AI Kick Drum Model on Your Old Linux Desktop with 6GB VRAM

#36

Post by kube-system »

lardosaurusrex wrote: post #8

I always roll my eyes when I see LLM weirdos talk about getting models to run on "old" hardware and finding out it's hardware that's still better than what most people have access to. It doesn't make it any less impressive to those who know what hardware requirements for LLMs usually is/are but for those with no idea it usually ends up reinforcing bitterness towards it as they feel annoyed that their own hardware is…

English adjectives are highly contextual. In this context, the author's clear meaning is in context to the current generative AI boom.

Re: How to Train a Gen AI Kick Drum Model on Your Old Linux Desktop with 6GB VRAM

#39

Post by lightedman »

larme wrote: post #35
aw123 wrote: post #29

Earlier quoted context omitted.

How far are we from getting a general model that can resynthesize any instrumental audio sound without fiddling with any knobs, so that we can recreate instruments we hear from any song? Seems like it should exist by now?

For me creating the exact sound is not very interesting from sound designing perspective. You can always sample the real instrument. Like physical modeling synthesis, the interesting part is to compress the sound to some parameters that you can tweak and generate new sounds Another approach is VAE, which also you give your some latent embedding, you can tweak the embedding to generate new sound. However the meaning o…

"You can always sample the real instrument."

This doesn't really work on instruments like guitars. Open D sounds way different than fretted D on the E string. Timbre changes with position and it's one of the ways I determine where a player's hands are on the neck when I'm trying to play their song.

Post reply on HN