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

Jukebox

openai.com

Post reply on HN
Print view View original

21–30 of 134 posts

Re: Jukebox

#21

Post by adamnemecek »

MulliMulli wrote: post #19
adamnemecek wrote: post #13

Earlier quoted context omitted.

Weird. It loads for me and I do see visitors coming so it might be just you? Send me an email (my-hn-username@gmail) and I'll notify you when I launch.

Got a 500 error as well...

This is embarrassing, try reloading the page. I'm using some website builder, I guess I'll have to move somewhere else. It doesn't normally do this.

Re: Jukebox

#22

Post by alextheparrot »

I think work like this will really bring a whole new life to a lot of video game music. Today, we see some really great composers making cinematic-level music for video games, which is great. What worlds often miss is ambient sounds, a radio as you're driving or something that reacts to how you act (Actions per minutes go up, maybe the tempo does too?) without having to compose a TON of music.

Re: Jukebox

#24

Post by akmiller »

nabla9 wrote: post #5

I predict that in very near future you just write funny lyrics, select the style and vocalist you want and you get good sounding mediocre music. Then we hear it in - private events like weddings. - social media creators make their own music to go with their funny videos. Cheap theme music for streamers and podcasters. - Advertising. Shopping centres make lyrics that advertise products and play them to you as pop song…

Definitely a market for this. There are so many events that like to use music as background noise but due to licensing restrictions in music you have to be careful what you use.

Re: Jukebox

#25

Post by squarefoot »

nabla9 wrote: post #5

I predict that in very near future you just write funny lyrics, select the style and vocalist you want and you get good sounding mediocre music. Then we hear it in - private events like weddings. - social media creators make their own music to go with their funny videos. Cheap theme music for streamers and podcasters. - Advertising. Shopping centres make lyrics that advertise products and play them to you as pop song…

The future will be AI lawyers battling for rights of AI generated music in the style of deceased artists on behalf of AI media corporations at the expense of robotic listeners.

Before all of this, we'll probably see improvised bands of deceased artists playing together AI generated music in their own style, not to mention long dead actors appearing in new movies etc. AI technology is going to give law firms a lot of work in the future.

Re: Jukebox

#26

Post by andybak »

This is the audio equivalent of "name one thing in this photo". Deep in the uncanny valley but fascinating.

We're getting closer. Music is proving to be a tough use case for generative ML.

Re: Jukebox

#27

Post by prafullasd »

tmoney1818 wrote: post #10

"the top-level prior has 5 billion parameters and is trained on 512 V100s for 4 weeks" If they used on-demand AWS instances, it would cost about 1,342,623 USD to train the top-level prior. So much for reproducing this work.

We release our model weights and code here https://github.com/openai/jukebox/, so you can directly build on top of them and don’t have to train from scratch

Re: Jukebox

#30

Post by grenoire »

Can anybody explain why the researchers are attempting to generate the whole song as a single waveform, as opposed to wiring generated MIDI into some instruments and separately a singing algorithm (perhaps a bit easier than the whole bulk work)?
Post reply on HN