Neural Amp Modeler Lv2 Save

Neural Amp Modeler LV2 plugin implementation

Project README


Bare-bones implementation of Neural Amp Modeler (NAM) models in an LV2 plugin.

There is no user interface. Setting the model to use requires that your LV2 host supports atom:Path parameters. Reaper does not. Carla and Ardour do. If your favorite LV2 host does not support atom:Path, let them know you want it. A Reaper feature request for this is here.

To get the intended behavior, you must run your audio host at the same sample rate the model was trained at (usually 48kHz) - no resampling is done by the plugin.

For amp-only models (the most typical), you will need to run an impulse reponse after this plugin to model the cabinet.

Models and Performance

The best source of models is ToneHunt.

NAM models are generally quite expensive to run. This isn't (much of) an issue on modern PCs, but you may have trouble running on less powerful hardware.

A Raspberry Pi 4 running a 64bit OS can run "standard" NAM models with a bit of room to spare for a cabinet IR and some lightweight effects.

If you are having trouble running a "standard" model, try looking for "feather" (the least expensive) models. You can find a list of "feather"-tagged models on ToneHunt. Note that tagging models is up to the submitter, so not all "feather" models are tagged as such - you should be able to find more if you dig around.


First clone the repository:

git clone --recurse-submodules -j4
cd neural-amp-modeler-lv2/build

Then compile the plugin using:


cmake .. -DCMAKE_BUILD_TYPE="Release"
make -j4


cmake.exe -G "Visual Studio 17 2022" -A x64 ..
cmake --build . --config=release -j4

Note - you'll have to change the Visual Studio version if you are using a different one.

After building, the plugin will be in build/neural_amp_modeler.lv2.

Open Source Agenda is not affiliated with "Neural Amp Modeler Lv2" Project. README Source: mikeoliphant/neural-amp-modeler-lv2
Open Issues
Last Commit
1 month ago

Open Source Agenda Badge

Open Source Agenda Rating