@Christoph-Hart
If I might throw my humble 2 cents in....and my 2 cents are change left over from a whole career of working in guitar amp modeling software, having spent almost 20 years with the ReValver amp modeling software and another 4 years with the HeadRush pedals and software. The software market segment of simulating hardware has completely turned from component level modeling to leveraging NN modeling. Neural Network modeling allows us to do in a matter off days what took months or years to accomplish, with better results (most of the time). Beyond guitar products, NN modeling lends itself to preamp, channel strip, etc modeling, which is why it's such an opportunity for @orange. This has really nothing to do with simply downloading models from tonehunt.org, this is about implementing something that will be "how it's done" from this moment on. Here's a real-world scenario: I am currently working for a guitar amplifier manufacturer that has a 60+ year history in guitar amps. They would like to release plugin versions of every flagship amp they have ever made AND ship a plugin version with every new amp that they design and release. This is my project, NN modeling is how to do it, and I have to find the solution that lets me get it done.
Having said that, I have really fallen in love with HISE in a short time, but it might not be a realistic solution (at this point) for my project. I would hate to see all this not properly implemented in HISE. It would be such a missed opportunity.

Having said all that.....we are about to enter the 2nd wave of NN modeling market disruption, which will truly change everything...again:

https://www.neuralampmodeler.com/post/the-first-publicly-available-parametric-neural-amp-model

Thanks for letting me get that out....

I have a great deal of experience with this, having worked on the HeadRush ReValver product for about 20 years. That product is all about representing famous gear. Legally, we do not have the right to use someone's trademark (logo, etc), so the common practice is to (1) name the product and design the logo in "spirit" of the source product and (2) put a disclaimer online and in the product stating that the brands implied are owned by the owners...lol. In the case of ReValver, we had an agreement with Peavey Electronics, Budda Amps, and Trace Elliot to use their actual logos and design, but you'd want that in writing.
If anyone has any specific questions regarding this....just hit me up. I'd be glad to help.

@sinewavekid
The snip found in this thread will get you going

https://forum.hise.audio/topic/10756/hardcoded-neural-network-does-not-work-as-expected/10

I know the NN topic has had it's share of coverage for a while now. Thanks to all the hard work and efforts of so many here, I've got working NN that loads AIDA-X guitar amp captures. Now my challenge is that I want to be able to swap out NN models at runtime based on a user selection. What I am seeing is that once I instantiate the NN and load in the initial model, I cannot load another model at runtime. The first loaded models stays firmly in place.

I am creating and loading the NN using the following:

const MLmodel = {MODEL JSON HERE};

const var tf = Engine.createNeuralNetwork("TensorFlowNetwork");

tf.loadTensorFlowModel(MLmodel);

I had assumed that, if I created multiple vars to hold the different models (MLmodel_1, MLmodel_2, etc), I could simply swap them out by calling ".loadTensorFlowModel(model)". But alas no.

Has anyone gotten something like this working? Any advise would be greatly appreciated.

Apologies if this has already been discussed....but I would think this would be low hanging fruit:

https://github.com/Tr3m/nam-juce

@Dan-Korneff - If memory serves me, I tried this and it didn't work for me. I think it's not fully cooked. I have only been able to get the Tensorflow/AIDA-X stuff to work.

I got it working!
Thanks to everyone for the help....it's greatly appreciated!

Hello all....
A project I'm working on has multiple convolution modules in a scriptnode network. I am attempting to load the IRs into the modules via scripting. It seems to be working, the convolution module is showing the name of the IR, but it's not actually loaded. If I manually load the IR in, it works.

To illustrate....the module on the left is loaded via script, but the module on the right in manually loaded. Although they both have the IR file name in the "label", only the one on the right actually loaded the IR.

So, here is the code in the function I'm using to "load" the IR. I know it can be simplified, but I figured it might be easier to follow this way

//create obj reference to cab 1 convolution modules and audio file slot
local CabIR1_1 = Synth.getAudioSampleProcessor("Cabinet1").getAudioFile(0);

//create variable to hold IR file name
// translates to something like: "PV 5150 412 Sheffield - SM57 - Cap.wav"
local CabIR1_1_wav = theCab1 + " - " + theMic1 + " - Cap.wav";

//load an iR into each of the convolution modules
CabIR1_1.loadFile(CabIR1_1_wav);

I hope that all makes sense? Thanks in advance!

@Oli-Ullmann
My understanding is that Claude (https://claude.ai/) is supposed to be much better than ChatGPT at writing usable code.

@Oli-Ullmann
That is amazing! If you don't mind me asking....could you share the prompt you used in ChatGPT?