Attached the model in case someone wants to look at it.
Posts made by ccbl
-
RE: Simple ML neural network
-
RE: Simple ML neural network
@Christoph-Hart so for now I decided to try and make a very simple audio processor using scriptnode. I followed the tutorial project adding the weights for the math.neural module to pickup, and it does see the object, however when I select it HISE crashes, complete CTD.
It's an LSTM network generated by a RTNeural based project (guitarML automatedguitarampmodelling pipline).
Not sure what the issue is.
-
RE: Simple ML neural network
@Christoph-Hart ok got it. Let's say I wanted to cascade two different NNs
I'm guessing these parts will have to be modified somehow in order to differentiate between the networks. Would it just be a case of "obj1"
and "obj2"`// This contains the JSON data from `Scripts/Python/sine_model.json` const var obj = // load the sine wave approximator network nn.loadPytorchModel(obj);
I'm pretty sure this is how you would set up the first part?
// We need to create & initialise the network via script, the scriptnode node will then reference // the existing network const var nn = Engine.createNeuralNetwork("NN1"); // We need to create & initialise the network via script, the scriptnode node will then reference // the existing network const var nn = Engine.createNeuralNetwork("NN2");
-
RE: Simple ML neural network
Trying to do a simple LSTM processor project. Where should one store their json files? Or do you paste in the weights directly? Using the ScriptNode Math function.
-
RE: Simple ML neural network
@Christoph-Hart Regarding the current RTNeural implementation.
With the GuitarML's AutomatedGuitarModelling LSTM trainer allows you to create parameterised models (https://github.com/GuitarML/Automated-GuitarAmpModelling).
With the NeuralNetwork module are you able to address these input parameters? I'm interested in a single input parameter and want to connect a knob to address this parameter in the model inference.
-
RE: Airwindows again
@Dan-Korneff Could you expand on this? I have very limited coding knowledge.
I'd like to utilise this transformer simulation AW Coils (https://github.com/airwindows/airwindows/blob/master/plugins/WinVST/Coils/CoilsProc.cpp)
And I think if I'm successful once I would know how to do it by myself in the future, if I wanted to use other DSP. A lot of his stuff is quite weird, but I think a few of his hardware emulations are quite useful used subtly as part of a signal chain.
-
RE: Troube with inverting control
Content.makeFrontInterface(600, 250); const var thresh = Content.getComponent("thresh"); inline function onsquashControl(component, value) { thresh.setValue(-24-value); }; Content.getComponent("squash").setControlCallback(onsquashControl);
This is what I used. It links the two controls nicely (as you can see from the video) but when the "thresh" knob is changed this way (via the "squash" knob") rather than directly manipulated the threshold (linked parameter) doesn't change.
-
Troube with inverting control
Hey folks, so in researching how to implement an inverted pot I found this post,
I used the snippet from this post. https://forum.hise.audio/topic/1882/inverting-knob/4?_=1720771370342The only problem is, when I manipulate the "stealth" knob manually it alters the linked parameter, however when I alter the user facing knob, the linking works, but the parameter doesn't change.
Video of the problem for reference
-
RE: Simple ML neural network
@Christoph-Hart said in Simple ML neural network:
@ccbl And can't you just convert the models to work in RTNeural? In the end it's just running maths and I'm not super interested in adding the same thing but in 5 variations.
I understand why you feel that way. There's no point chasing your tail every time a new NN comes on the scene. What I would say though is that since NAM has been released, I've seen at least 4 different companies bring out their own NN capture tech. And not a single one of those has taken off, all combined they have less captures publicly available than one comprehensive NAM pack on ToneHunt .
Multiple commercial companies have incorporated NAM including Melda, Amplifire, Two Notes, Audio Assualt, and Solemn Tones amongst others. AnalogueX now uses NAM to capture preamps and compressors. Past of Future also does this.
Essentially NAM has become the industry standard format for Analogue gear capture using neural networks at this point. So personally I think it would be worth implementing the NAM core tech as there's a far higher chance people are going to want to use a NAM model than any of the other tech.
Beggars can't be choosers though. I don't mean this to come across as a demand so much as trying to present a compelling case. I don't have the skills to implement this myself. I understand there's only some much time and will power a person has to dedicate to a project like this.
So I'm highly grateful for any way to incorporate NAM into the signal processing using HISE. Whether that involves conversion or native processing.
-
RE: New to HISE [came to make some audio FX plugins] Issue finding VST3 output
@Christoph-Hart Awesome thanks! This is such an unbelievable tool. Can't wait to learn more about it all.
-
RE: New to HISE [came to make some audio FX plugins] Issue finding VST3 output
Now that I can compile plugins, are there any getting started resources for audio plugins? There are some great ones for instruments but looking at the example project I'm not sure if there are special things I need to do, for instance to get script node to take audio input. Or is that taken care of by exporting as an Audio FX compared to the Instrument export?
-
RE: New to HISE [came to make some audio FX plugins] Issue finding VST3 output
Well not sure what the issue was. I decided to start fresh on a a different windows install.
Installed VS -> Installed OneAPI -> Extract Source -> Compile.
On my new system it all works flawlessly.
-
RE: New to HISE [came to make some audio FX plugins] Issue finding VST3 output
Tried running the setup wizard and this screen seems to confirm IPP should be working.
-
RE: Simple ML neural network
I think the only issue with conversion will be that most NAM models are wavenet which is not currently supported by RTNeural.
NAM has been tuned specifically around this architecture which is one of the reasons it's currently considered the most realistic.
Whether or not this poses a barrier to conversion, and if in conversion you will loose some of the realism that has been achieved I'm not sure. I think as stated real time performance will likely be the same. NAM currently operates with zero latency, which I think RTNeural also does from memory, it's really about CPU utilisation.
-
RE: New to HISE [came to make some audio FX plugins] Issue finding VST3 output
Just to be sure I re-installed OneAPI and made sure the VS2022 integration was checked. I then cleaned my HISE build and went to follow the advice on the the Intel page
"Go to Project> <your_project_name> Properties> Configuration Properties> Intel Libraries for oneAPI."
But I don't see an option for Intel Libraries in the HISE Project Properties in VS.
I tried building again and exporting the Parametric EQ project to VST and still get the same error.
-
RE: New to HISE [came to make some audio FX plugins] Issue finding VST3 output
@ccbl various versions of this same error.
G:\Coding\HISE\HISE-develop\hi_streaming\hi_streaming.h(74,10): error C1083: Cannot open include file: 'ipp.h': No such
file or directory [G:\Coding\HISE Tutorial\ParametriqEQ\Binaries\Builds\VisualStudio2022\ParametriqEQ_SharedCode.vcxpr
oj]I can confirm the file exists in the OneAPI folder though.
-
RE: New to HISE [came to make some audio FX plugins] Issue finding VST3 output
@d-healey Yeah I installed the through the OneAPI.
-
RE: New to HISE [came to make some audio FX plugins] Issue finding VST3 output
@d-healey Thanks, I did that using VS2022 and compiles HISE just fine. I'm having issues with the Intel IPP include though on plugin export.
I followed your advice from this thread [https://forum.hise.audio/topic/3653/ipp-missing-in-plugin-export/25?_=1619258101981] with adding the include and libraries etc in projucer.
Is there a particular version of IPP that is known to work?
-
RE: Simple ML neural network
@Christoph-Hart A few things I guess. The number of NAM captures currently dwarfs all the other that are supported by RTNeural (I have used guitar ML in the past for instance) and it's only growing (here for example https://tonehunt.org/). Not just 1000s of amp snap shots but people are really getting into studio gear captures too. There's a huge group of people for support in generating good captures and technical training support. And of course it is probably the best sounding in terms of accuracy right now.
I'm interested enough in using a neural net that I'm willing to use RTNeural, it's still a great system. NAM is becoming a defacto standard in a lot of NN capture spaces currently though. So for the future it seems like a good addition to the code base. And on a personal level I've already created over 1000 NAM models.
Maybe once I've learned more of the basics, if someone is willing to help me with it I would appreciate it.