Jukebox
openai.com
Jukebox
1–10 of 134 posts
Re: Jukebox
#2From 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.
Re: Jukebox
#3From 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.
Isn’t that superhuman?
I would guess that on average, it takes a professional more than 36 hours ((4×60÷20)×3) to make a 4-minute audio track with original music based on given lyrics.
Re: Jukebox
#4From 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.
Isn’t that superhuman? I would guess that on average, it takes a professional more than 36 hours ((4×60÷20)×3) to make a 4-minute audio track with original music based on given lyrics.
The professional's output would be a lot more listenable, though, most likely!
Re: Jukebox
#5I 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 songs. Some bubs make their own songs.
Re: Jukebox
#6Earlier quoted context omitted.
Isn’t that superhuman? I would guess that on average, it takes a professional more than 36 hours ((4×60÷20)×3) to make a 4-minute audio track with original music based on given lyrics.
The professional's output would be a lot more listenable, though, most likely!
Definitely!
It’s impressive that now, they “only” need to improve the quality for it to outcompete professional musicians on commercial delivery.
Re: Jukebox
#7From 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.
Eh. It's built on Transformers, and people have already demonstrated considerable model distillation/compression on those just like every other kind of NN, and as they note, once you've trained a teacher model, you can probably train a wide flat model for similar results. (As I recall, WaveNet used to be similarly slow, but even without the parallel WaveNet retraining, with proper caching of repeated states, you could make it orders of magnitude faster and approach realtime.)
Re: Jukebox
#8Well I'm glad to know that music won't be made by AI anytime soon, if this is the best we can do. :)
This project is very interesting, but it goes to show just how far we still have to come before AI is replacing creativity.
Re: Jukebox
#9I'm working on an IDE for music composition.
Launching soon.
Music is fundamentally unsolvable by AI. We'll have AI writing code before we'll have AI writing meaningful music.
Re: Jukebox
#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.