This repository handles training, reamping, and exporting the weights of a model. For playing trained models in real time in a standalone application

sdatkinson/neural-amp-modeler

submited by

Style Pass

2023-03-18 14:00:07

This repository handles training, reamping, and exporting the weights of a model. For playing trained models in real time in a standalone application or plugin, see the partner repo, NeuralAmpModelerPlugin.

If you don't have a good computer for training ML models, you use Google Colab to train in the cloud using the pre-made notebooks under bin\train.

For the very easiest experience, simply go to https://colab.research.google.com/github/sdatkinson/neural-amp-modeler/blob/main/bin/train/easy_colab.ipynb and follow the steps!

For users looking to get more fine-grained control over the modeling process, NAM includes a training script that can be run from the terminal, e.g.:

where config_data.json contains the information about the data you're training on, config_model.json contains information about the model architecture that is being trained, and config_learning.json contains information about the training run itself (e.g. number of epochs). You'll need to configure the data JSON to the specifics of the data you're training on. The others may work for your needs out-of-the-box with no modification.

Since NAM uses PyTorch Lightning under the hood as a modeling framework, many of the configuration options that are passed to its componenets can be configured from the data/model/learning JSONs.