Bark: A transformer based text to audio system • Hacker News Board

Re: Bark: A transformer based text to audio system

#11

Post by exitb » Mon, May 15, 2023, 8:27 AM UTC

Oh, that's interesting - I've played the Polish bit from the examples page [1] and it's quite heavily accented. Like a foreign national learning the language. Do the other non-English examples also sound somewhat off to native speakers?

[1] https://suno-ai.notion.site/Bark-Examples-5edae8b02a604b54a4...

Re: Bark: A transformer based text to audio system

#12

Post by UhUhUhUh » Mon, May 15, 2023, 8:37 AM UTC

Nice. Thank you Suno! This is very good and will fit perfectly in my current projects. I feel like hugging your face.

Re: Bark: A transformer based text to audio system

#13

Post by MitPitt » Mon, May 15, 2023, 8:44 AM UTC

The inability to train custom voices makes this useless for anything except generic TTS.

Why do AI devs keep shooting their own projects in the foot? This trend is upsetting me so much.

Re: Bark: A transformer based text to audio system

#14

Post by marban » Mon, May 15, 2023, 8:50 AM UTC

Has someone played with the opposite in a sense of not only recognising words but also evaluating their correct pronunciation?

Re: Bark: A transformer based text to audio system

#15

Post by shrx » Mon, May 15, 2023, 8:59 AM UTC

qup wrote: post #10

Can we run this locally? (on normal machines?) How fast are generations on consumer machines?

From the README:

> You can now use Bark with GPUs that have low VRAM (<4GB).

Re: Bark: A transformer based text to audio system

#16

Post by JonathanFly » Mon, May 15, 2023, 9:02 AM UTC

qup wrote: post #10

Can we run this locally? (on normal machines?) How fast are generations on consumer machines?

It's like 50% realtime on a 3090, not quite real time on a 4090. You can also use smaller models and it's a bit faster.

3080 is same speed, you don't need the extra memory.

Re: Bark: A transformer based text to audio system

#17

Post by villgax » Mon, May 15, 2023, 9:04 AM UTC

Another repost of a safe-guarding model, it's just obnoxious how the write-up for Do No Evil has become, like how Stability doesn't want you to do illegal things with their outputs or these guys not letting you build a custom voice model.

Re: Bark: A transformer based text to audio system

#18

Post by JonathanFly » Mon, May 15, 2023, 9:19 AM UTC

exitb wrote: post #11

Oh, that's interesting - I've played the Polish bit from the examples page [1] and it's quite heavily accented. Like a foreign national learning the language. Do the other non-English examples also sound somewhat off to native speakers? [1] https://suno-ai.notion.site/Bark-Examples-5edae8b02a604b54a4...

It's just a characteristic of some of the default voices. I made some perfect French voices by having somebody on Discord check for native accents, because otherwise I can't tell. Once somebody does this for every language it should be all set. (Somebody who isn't me though, it takes awhile and I'm just playing around a bit, don't even have a use case for TTS honestly.)

Re: Bark: A transformer based text to audio system

#19

Post by nils-herzig » Mon, May 15, 2023, 9:22 AM UTC

exitb wrote: post #11

Oh, that's interesting - I've played the Polish bit from the examples page [1] and it's quite heavily accented. Like a foreign national learning the language. Do the other non-English examples also sound somewhat off to native speakers? [1] https://suno-ai.notion.site/Bark-Examples-5edae8b02a604b54a4...

The German example sounds fine. The second code switching example has a German part, which has an accent for a brief moment.

Re: Bark: A transformer based text to audio system

#20

Post by red75prime » Mon, May 15, 2023, 9:42 AM UTC

MitPitt wrote: post #13

The inability to train custom voices makes this useless for anything except generic TTS. Why do AI devs keep shooting their own projects in the foot? This trend is upsetting me so much.

Probably because if they are seen as enablers of scams, they'll be shot by someone else.