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

VibeVoice: Open-source frontier voice AI

github.com

Post reply on HN
Print view View original

91–100 of 191 posts

Re: VibeVoice: Open-source frontier voice AI

#91

Post by hedora »

jrm4 wrote: post #74
psychoslave wrote: post #70

Earlier quoted context omitted.

With free libre software, where freedom and liberty are about what the end user is empowered with actually, the software is mostly metonymic. Free software, free society, because there are free people in the middle of course.

Right, as I said elsewhere, maybe let's just let "open-source" have it. "Open-source" can be "anything you can go out and grab a copy of and use" but doesn't give you much legal certainty about any of it, and reserve "free software" for the other, better thing.

But, free software lost it's way around GPLv3. From the end user's perspective, GPLv3 says that you can only use the software if it's either a cloud service, on hypothetical open firmware devices, or if you install it yourself.

AGPLv3 partially solves the issue by blocking people like Google from using it to build proprietary cloud services that take away their users' freedom. (It still doesn't solve the problem where providers use network effects to achieve the same end game.)

Re: VibeVoice: Open-source frontier voice AI

#92

Post by GuinansEyebrows »

lblock wrote: post #15
steinvakt2 wrote: post #10

This is not a new model. Also, it hallucinates a lot. Also, it's very heavy and slow in inference. It's also bad in multilingual. Edit: I'm talking purely about speech to text (STT). Not sure about the other things this can do.

Yeah, I don't get why it is suddenly getting so much attention today, it is all over twitter too

there is so much more subversive marketing out there than any of us can really fathom. i try not to be too paranoid but it's getting a lot harder every day.

i know someone who worked in what we might call the 'astroturfing' space within the entertainment industry. after having a few discussions with him and with things like this[0] becoming more known, it's really difficult to afford any assumption of organic intent when money is on the line - especially at the scale that microsoft works at compared to something as comparatively quaint as the music industry.

[0] https://www.wired.com/story/geese-chaotic-good-marketing-ind...

Re: VibeVoice: Open-source frontier voice AI

#93

Post by gagan2020 »

steinvakt2 wrote: post #10

This is not a new model. Also, it hallucinates a lot. Also, it's very heavy and slow in inference. It's also bad in multilingual. Edit: I'm talking purely about speech to text (STT). Not sure about the other things this can do.

It is not good for text to speech (TTS) as well. I am trying it for few days. First of all 1.5B model documentation is not there. 0.5B realtime is shit model. I was converting text, line by line and it was randomly adding music and couldn't handle special characters like "…".

I really disappointed with this model to say the least.

Re: VibeVoice: Open-source frontier voice AI

#94

Post by MarsIronPI »

hedora wrote: post #91
jrm4 wrote: post #74

Earlier quoted context omitted.

Right, as I said elsewhere, maybe let's just let "open-source" have it. "Open-source" can be "anything you can go out and grab a copy of and use" but doesn't give you much legal certainty about any of it, and reserve "free software" for the other, better thing.

But, free software lost it's way around GPLv3. From the end user's perspective, GPLv3 says that you can only use the software if it's either a cloud service, on hypothetical open firmware devices, or if you install it yourself. AGPLv3 partially solves the issue by blocking people like Google from using it to build proprietary cloud services that take away their users' freedom. (It still doesn't solve the problem wher…

> From the end user's perspective, GPLv3 says that you can only use the software if it's either a cloud service, on hypothetical open firmware devices, or if you install it yourself.

What in the world do you mean?

Re: VibeVoice: Open-source frontier voice AI

#95

Post by scotty79 »

maxloh wrote: post #14

I think we should stop calling this type of models open source. They are indeed "open weight." The training code is proprietary and never revealed. https://github.com/microsoft/VibeVoice/issues/102

Open weights is not exactly right either because we do get source of the software that uses those open weights.

Maybe open inference?

But we often also get source code for fine tunning the model.

So maybe it's closer to open source than to anything else?

Isn't it a bit like not calling a game open source because engine tooling used to made it isn't open source and they didn't publish .psd files with asset designs?

Re: VibeVoice: Open-source frontier voice AI

#96

Post by scotty79 »

steinvakt2 wrote: post #10

This is not a new model. Also, it hallucinates a lot. Also, it's very heavy and slow in inference. It's also bad in multilingual. Edit: I'm talking purely about speech to text (STT). Not sure about the other things this can do.

You just saved me an afternoon.

Re: VibeVoice: Open-source frontier voice AI

#97

Post by data-ottawa »

simonw wrote: post #84
maxloh wrote: post #14

I think we should stop calling this type of models open source. They are indeed "open weight." The training code is proprietary and never revealed. https://github.com/microsoft/VibeVoice/issues/102

I'm reserving that complaint for "open source" models which are released under non-open-source licenses. I care that I know what I can DO with the project when I see it described as "open source".

That would be “permissive license”

Maybe we should have a little cue card for models: vendor/name, size, open weights, open source, permissive license.

It’s simple enough an idea.

Re: VibeVoice: Open-source frontier voice AI

#98

Post by scotty79 »

xnx wrote: post #79

Still waiting for the open weights model that conclusively beats the multi-year old Whisper in accuracy, features, and performance.

It's crazy that a lot is happening in open models for stt, but there's very little progress when it comes to results, esp multilingual.

Re: VibeVoice: Open-source frontier voice AI

#99

Post by ryandrake »

accrual wrote: post #34
aqme28 wrote: post #28

Interesting to see "vibe" enshrined by the likes of Microsoft as an AI product word.

Especially when "vibe coded" can have a negative connotation meaning quickly put together without understanding.

In my mind, Vibe-anything means "some slop carelessly thrown together to ship as fast as possible." Wild that it's being used in a serious product name!

Re: VibeVoice: Open-source frontier voice AI

#100

Post by simonw »

yjftsjthsd-h wrote: post #90
simonw wrote: post #84

Earlier quoted context omitted.

I'm reserving that complaint for "open source" models which are released under non-open-source licenses. I care that I know what I can DO with the project when I see it described as "open source".

> I care that I know what I can DO with the project when I see it described as "open source". Yes, the first of which is that you should be able to build it from source. Which requires the source code, and in this case data.

The OSI's take on this is that an open source model can be modified through fine-tuning etc, even if you can't rebuild it from scratch.

The problem with requiring "build from scratch" for open source models is that the number of interesting models with training data that can be openly licensed is close to zero.

If you trained your model on an unlicensed scrape of the web you can't release the data under an open source license!

The Open Source Initiative have a bunch of their thinking around this in their FAQ for the "Open Source AI definition": https://opensource.org/ai/faq#isn-t-training-data-required-t...

Post reply on HN