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

171–180 of 191 posts

Re: VibeVoice: Open-source frontier voice AI

#171

Post by LtWorf »

hedora wrote: post #131
MarsIronPI wrote: post #94

Earlier quoted context omitted.

> 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?

The anti-tivo clause bans things like Apple pre-installing GPLv3 software on macs, but allows them to let you use exactly the same software as long as they do not give users access to the binary. AGPLv3 blocks both use cases, GPLv2 blocks neither. On the spectrum of "things that take away user freedom", withholding the source code is bad. Withholding the source code, the binaries and physical access to the computer i…

It doesn't ban apple from doing anything. They choose to avoid a license that was better for the users.

Re: VibeVoice: Open-source frontier voice AI

#173

Post by maxloh »

simonw wrote: post #100
yjftsjthsd-h wrote: post #90

Earlier quoted context omitted.

> 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 sourc…

That's a point.

It is legal to train on copyrighted materials, provided they were obtained legally. Most companies also train their models using user interactions with previous iterations.

It is impossible to release this data publicly, let alone license it to a third party. However, I believe that at least the training code and the data processing pipeline could, and should, be released in order to claim a model is truly "open source."

That said, Allen AI actually released several models with the full datasets available. It is impressive how they pushed the models' performance despite training on a limited set of publicly available data. Kudos to them.

Re: VibeVoice: Open-source frontier voice AI

#177

Post by ipotapov »

I built speech-swift, which focuses on on-device speech processing like VibeVoice, but specifically leverages Apple Silicon's capabilities for ASR, TTS, and VAD without cloud dependency. Our ASR supports 52 languages with a real-time factor of 0.06. https://soniqo.audio/benchmarks

Re: VibeVoice: Open-source frontier voice AI

#178

Post by steinvakt2 »

narrationbox wrote: post #165
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.

Yes, the SOTA is currently much more advanced.

What do you consider to be SOTA?

Re: VibeVoice: Open-source frontier voice AI

#179

Post by LtWorf »

MarsIronPI wrote: post #168
hedora wrote: post #127

Earlier quoted context omitted.

The point of the Free in free software was always to protect the users of the software, not the vendors or the redistributors. (This is why the license focuses on the redistributors -- the mechanisms of the license limit their rights in order to protect others' rights.) The first sentence of the GNU manifesto says this, and a few sections later in the document elaborate on the point: https://www.gnu.org/gnu/manifesto…

I see your point and I agree. It's just that when you say "GPLv3 says that you can only use the software if it's either a cloud service, hypothetical open firmware devices" that's a stretch and not really true. AIUI vendors can pre-install GPLv3 software as long as they let you actually then replace the software (i.e. no DRM or locked bootloader). The firmware can still be non-GPL and non-replaceable. You just can't…

AFAIK you can use GPLv3 for non-replaceable stuff. The thing is only to allow the users to replace it IIF it's phisically possible to do so. If you make a device that boots from a ROM it's not a problem. If you sign your updates and keep your public key on a ROM and there is no way to boot anything else… there's a problem.

Re: VibeVoice: Open-source frontier voice AI

#180

Post by LtWorf »

simonw wrote: post #100
yjftsjthsd-h wrote: post #90

Earlier quoted context omitted.

> 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 sourc…

I think the OSI no longer has any authority since that stunt they pulled in their "elections".
Post reply on HN