Viewing profile — gkucsko

Our models support full 2+ mins of coherent generation but generating a couple of verses at a time through continue gives good results you can keep picking the continuations that s…

We’re US based but come from pretty much across the globe and my wife is Punjabi, so yeah that’s the origin of the name :)

yeah sometimes there are definitely artifacts. technically they can be removed pretty easily with another model (like denoiser from FB) but for now we wanted to keep it simple to l…

history is semantic, coarse and fine. so essentially the same thing thats getting generated just using it as an input before the generation

thanks, the model itself is a pretty vanilla gpt model based heavily on karpathy's nanogpt, so should not need too many bells and whistles to get it running on specific architectur…

Hey, one of the Suno founders/creators of Bark here. Thanks for all the comments, we love seeing how we can improve things in the future. At Suno we work on audio foundation models…

haha https://demo.suno.ai

history prompts are just unconditionally generated TTS from the same model. any of those can be used as history, but for convenience 10 are provided for each language (to generate …

it's more meant to show code switching. more examples here: https://suno-ai.notion.site/Bark-Examples-5edae8b02a604b54a4...

Thanks :) Let us know if you come across interesting findings!

Thanks! The model learns a lot from unsupervised (as well as supervised) audio, so technically low-quality and high-quality audio are both just as likely to the model as music, bac…

There is no sign-up (microsoft account or similar) necessary, the broadcast link is much shorter and easier to share, and it's open source :)