NAM: Neural Amp Modeler

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.

How to use

There are three main ways to use the NAM trainer. There are two simplified trainers available (1) in your browser via Google Colab and (2) Locally via a GUI. There is also a full-featured trainer for power users than can be run from the command line.

Google Colab

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, open easy_colab.ipynb on Google Colab and follow the steps!

GUI

After installing the Python package, a GUI can be accessed by running nam in the command line.

The command line trainer (all features)

Alternatively, you can clone this repo to your computer and use it locally.

Installation

Installation uses Anaconda for package management.

For computers with a CUDA-capable GPU (recommended):

conda env create -f environment_gpu.yml

Note: you may need to modify the CUDA version if your GPU is older. Have a look at nVIDIA's documentation if you're not sure.

Otherwise, for a CPU-only install (will train much more slowly):

conda env create -f environment_cpu.yml

Note: if Anaconda takes a long time "Solving environment...", then you can speed up installing the environment by using the mamba experimental sovler with --experimental-solver=libmamba.

Then activate the environment you've created with

conda activate nam

Train models (GUI)

After installing, you can open a GUI trainer by running

nam

from the terminal.

Train models (Python script)

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. In order to run it

Download audio files

Download the v1_1_1.wav and output.wav to a folder of your choice

Update data configuration

Edit bin/train/data/single_pair.json to point to relevant audio files:

    "common": {
        "x_path": "C:\\path\\to\\v1_1_1.wav",
        "y_path": "C:\\path\\to\\output.wav",
        "delay": 0
    }

Run training script

Open up a terminal. Activate your nam environment and call the training with

python bin/train/main.py \
bin/train/inputs/data/single_pair.json \
bin/train/inputs/models/demonet.json \
bin/train/inputs/learning/demo.json \
bin/train/outputs/MyAmp

data/single_pair.json contains the information about the data you're training on
models/demonet.json contains information about the model architecture that is being trained. The example used here uses a feather configured wavenet.
learning/demo.json contains information about the training run itself (e.g. number of epochs).

The configuration above runs a short (demo) training. For a real training you may prefer to run something like,

python bin/train/main.py \
bin/train/inputs/data/single_pair.json \
bin/train/inputs/models/wavenet.json \
bin/train/inputs/learning/default.json \
bin/train/outputs/MyAmp

As a side note, NAM uses PyTorch Lightning under the hood as a modeling framework, and you can control many of the Pytorch Lightning configuration options from bin/train/inputs/learning/default.json

Export a model (to use with the plugin)

Exporting the trained model to a .nam file for use with the plugin can be done with:

python bin/export.py \
path/to/config_model.json \
path/to/checkpoints/epoch=123_val_loss=0.000010.ckpt \
path/to/exported_models/MyAmp

Then, point the plugin at the exported model.nam file and you're good to go!

Standardized reamping files

NAM can train using any paired audio files, but the simplified trainers (Colab and GUI) can use some pre-made audio files for you to reamp through your gear.

You can use any of the following files:

Other utilities

Run a model on an input signal ("reamping")

Handy if you want to just check it out without needing to use the plugin:

python bin/run.py \
path/to/source.wav \
path/to/config_model.json \
path/to/checkpoints/epoch=123_val_loss=0.000010.ckpt \
path/to/output.wav

slives-lab / neural-amp-modeler Goto Github PK

neural-amp-modeler's Introduction