Audacity has added AI audio editing capabilities thanks to Intel’s free OpenVINO plugins. These plugins add AI-powered noise suppression, speech transcription, music generation and remixing, and music separation to the freeware sound editor and are available for download today.
[Edit: indeed, its actually good that it’s 2gb]
2gb plugin??!
Btw, does it work with tenacity?
AI models are often multiple gigabytes, tbh it’s a good sign that it’s not “AI” marketing bullshit (less of a risk with open source projects anyway). I’m pretty wary of “AI” audio software that’s only a few megabytes.
Tensorflowlite models are tiny, but they’re potentially as much an audio revolution as synthetizer were in the 70s. It’s hard to tell if that’s what we’re looking at here.
Why are they that big? Is it more than code? How could you get to gigabytes of code?
Currently, AI means Artificial Neural Network (ANN). That’s only one specific approach. What ANN boils down to is one huge system of equations.
The file stores the parameters of these equations. It’s what’s called a matrix in math. A parameter is simply a number by which something is multiplied. Colloquially, such a file of parameters is called an AI model.
2 GB is probably an AI model with 1 billion parameters with 16 bit precision. Precision is how many digits you have. The more digits you have, the more precise you can give a value.
When people talk about training an AI, they mean finding the right parameters, so that the equations compute the right thing. The bigger the model, the smarter it can be.
Does that answer the question? It’s probably missing a lot.
It’s basically a huge graph/flowchart.
It’s really nothing of the sort.
There are graph neural networks (meaning NNs that work on graphs), but I don’t think that’s what is used here.
I do not understand what you mean by “routes”. I suspect that you have misunderstood something fundamental.
You can see a neural net as a graph in that the neurons are connected nodes. I don’t believe that graph theory is very helpful, though. The weights are parameters in a system of linear equations; the numbers in a matrix/tensor. That’s not how the term is used in graph theory, AFAIK.
ETA: What you say about “routes” (=paths?) is something that I can only make sense of, if I assume that you misunderstood something. Else, I simply don’t know what that is talking about.
They’re composed of many big matrices, which scale quadratically in size. A 32x32 matrix is 4x the size of a 16x16 matrix.
The current wave of AI is around Large Language Models or LLMs. These are basically the result of a metric fuckton of calculation results generated from running a load of input data in, in different ways. Given these are often the result of things like text, pictures or audio that have been distilled down into numbers, you can imagine we’re talking a lot of data.
(This is massively simplified, by someone who doesn’t entirely understand it themselves)
deleted by creator
It seems reasonable given it includes multiple AI models.
2gb is pretty normal for an AI model. I have some small LLM models on my PC and they’re about 7-10gb big. The big ones take up even more space.
Isn’t tenacity a joke project made by 4channers
That fork is sneedacity, which is very dead.
Gotcha, thank you for the info. Gotta admit their made-up words are pretty funny
Tenacity is a Audacity fork without telemetry
Isn’t the telemetry in Audacity opt-in anyway?
The fork was created when Audacity was bought and one of the first things the new developers were about to do was add opt-out telemetry. People didn’t like that at all. From what I read in this thread, they ended up adding opt-in telemetry instead.
It should be now, but it wasn’t the case when they introduced it