Jukebox • Hacker News Board

Re: Jukebox

#131

Post by mycall » Sun, May 03, 2020, 4:25 PM UTC

mcleaveypayne wrote: post #38

grenoire wrote: post #30

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)?

We did work last year on MIDI alone - https://openai.com/blog/musenet/ and some early work now on conditioning the raw audio based on MIDI (early results at the bottom of the Jukebox blog). Agreed though there should be interesting results from modeling different blends of MIDI, stem, and raw audio data. Raw audio alone gives us the most flexibility in terms of the kinds of sounds we can create, but it's also the mos…

Something like MOD/XM music comes to mind.

Re: Jukebox

#132

Post by MarioMan » Mon, May 04, 2020, 3:16 PM UTC

minimaxir wrote: post #2

From the GitHub repo: "On a V100, it takes about 3 hrs to fully sample 20 seconds of music." That might make building off this project out of reach of the average engineer (you certainly cannot build that into a Colab notebook), although that necessary amount of compute is not surprising.

They added a link to a Colab notebook. The upsampling takes most of that time, so if you're wiling to deal with a noisy and compressed sounding piece, it's actually very doable.

Re: Jukebox

#133

Post by squarefoot » Mon, May 04, 2020, 3:23 PM UTC

TeMPOraL wrote: post #115

squarefoot wrote: post #25

Earlier quoted context omitted.

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…

This subthread made me immediately think of: "If you want a vision of the future, imagine a human face booting on a stamp forever." (From the last story at https://slatestarcodex.com/2016/10/17/the-moral-of-the-story... )

One of the many many examples of why the 2006 Idiocracy docu^h^h^hmovie would well deserve a sequel. Probably even two, considering how much material we produced since then.

Re: Jukebox

#134

Post by the8472 » Tue, May 05, 2020, 12:05 AM UTC

alkibiades wrote: post #68

sdan wrote: post #47

Earlier quoted context omitted.

Just know that: much of the stuff OpenAI and other research orgs put out (including mine) are heavily cherry-picked. Most of the time its pumps out gibberish, but in the off chance it doesn't it gets used as marketing material.

monkey writing shakespeare

There is a huge chasm between more monkeys than atoms in the universe typing scripts unseen and a bunch of GPUs generating a few hundred samples from which researchers can cherry-pick.