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

Bark – Text-prompted generative audio model

github.com

Post reply on HN
Print view View original

51–60 of 99 posts

Re: Bark – Text-prompted generative audio model

#51

Post by dasickis »

calny wrote: post #7

Very cool. Side note: bark-gpt.com is already taken for a dog translator: "The world’s first AI powered, real-time communications tool between humans and their furry best friends."[0] I only know this because my law firm partner's name is Bark, and I wanted to automate some legal work and name the software "Bark GPT" after him. [0] https://www.bark-gpt.com/

This is an April Fool's joke[1] and really good! We're doing this for real: https://sarama.app.

Reference:

1. https://www.laika.berlin/en/blog/new-client-barkgpt-ai-dog-b...

Re: Bark – Text-prompted generative audio model

#53

Post by newswasboring »

Man I know this is HN, and I know we have a certain decorum we should be maintaining, but with the recent activity in this field the most appropriate response to these posts is "4bit when?" or "f16 when?". Not sure which one is applicable. I am having no luck running it on a 6GB vram gpu, so I guess its the 16 bit floating point one.

Re: Bark – Text-prompted generative audio model

#54

Post by dmix »

gkucsko wrote: post #23

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, creating speech, music, sounds effects etc…. Text to speech was a natural playground for us to share with the community and get some feedback. Given that this model is a full GPT model, the text input is merely a guidance and the model ca…

How are the voices determined? Is there an option or is it just random/based on the prompts like "WOMAN"?

Re: Bark – Text-prompted generative audio model

#55

Post by drowsspa »

miki123211 wrote: post #42

The fact that this is open source and can generate more thann just speech is really nice, but for speech itself, it's much lower quality than what Eleven Labs provides. All the open source models I've seen so far have this weird kind of neural fuzziness to them. I don't know what Eleven does better, but there's definitely a big difference.

Seems like it's doable to fix it in post, but I guess nowadays we're all about just shoving everything into the model

Re: Bark – Text-prompted generative audio model

#56

Post by cyberax »

bdg wrote: post #52

Ok, the German example caught me -- it's too real. "But maybe it would be faster if..."

On the other hand, Russian was disappointing. It put a stress in one word incorrectly (it confused the grammatical form, used the genitive case instead of the accusative) and in general sounded strange.

Re: Bark – Text-prompted generative audio model

#58

Post by ttul »

gkucsko wrote: post #26
turnsout wrote: post #24

Earlier quoted context omitted.

Amazing work so far! Do you have any sense about how difficult it would be to enable M1/M2 or CoreML support?

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 architectures. that said i have very little experience with platform specific development, so would looove some help from the community :)

A serious nod to Karpathy here. They could have chosen any other Transformer architecture, but chose perhaps the most reachable one - in the literal sense.

Re: Bark – Text-prompted generative audio model

#59

Post by ttul »

gkucsko wrote: post #23

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, creating speech, music, sounds effects etc…. Text to speech was a natural playground for us to share with the community and get some feedback. Given that this model is a full GPT model, the text input is merely a guidance and the model ca…

This tech will be used by crooks to automate attacks. Generate the language using GPT-4 and the audio using Bark, and then start making phone calls. Because it’s open source, all you need is GPUs. This is not a criticism. I’m impressed and grateful for the openness. Everyone needs to wake up and recognize that these attacks are coming at us essentially right now.

Re: Bark – Text-prompted generative audio model

#60

Post by montebicyclelo »

newswasboring wrote: post #53

Man I know this is HN, and I know we have a certain decorum we should be maintaining, but with the recent activity in this field the most appropriate response to these posts is "4bit when?" or "f16 when?". Not sure which one is applicable. I am having no luck running it on a 6GB vram gpu, so I guess its the 16 bit floating point one.

related to this - to those releasing models, it would be great if you could share how much VRAM is required (seems very common for this key piece of info to be missing).
Post reply on HN