https://github.com/GuitarML/SmartGuitarAmp

Guitar plugin made with JUCE that uses neural networks to emulate a tube amplifier.
https://github.com/GuitarML/SmartGuitarAmp

audio-processing guitar juce machinelearning neuralnetworks

Last synced: about 8 hours ago
JSON representation

Guitar plugin made with JUCE that uses neural networks to emulate a tube amplifier.

• Host: GitHub
• URL: https://github.com/GuitarML/SmartGuitarAmp
• Owner: GuitarML
• License: apache-2.0
• Created: 2020-09-08T15:00:15.000Z (about 4 years ago)
• Default Branch: main
• Last Pushed: 2023-04-11T18:03:36.000Z (over 1 year ago)
• Last Synced: 2024-11-05T13:26:36.155Z (7 days ago)
• Topics: audio-processing, guitar, juce, machinelearning, neuralnetworks
• Language: C++
• Homepage: https://guitarml.com/
• Size: 6.63 MB
• Stars: 1,235
• Watchers: 24
• Forks: 55
• Open Issues: 3
• Metadata Files:
  • Readme: README.md
  • Funding: .github/FUNDING.yml
  • License: LICENSE.txt

Awesome Lists containing this project

• awesome-juce - SmartGuitarAmp - 2.0|1237| 1 year_^🟠| (Effects)

README

        
# SmartGuitarAmp

[![Downloads](https://img.shields.io/github/downloads/GuitarML/SmartGuitarAmp/total)](https://somsubhra.github.io/github-release-stats/?username=GuitarML&repository=SmartGuitarAmp&page=1&per_page=30) [![CI](https://github.com/GuitarML/SmartGuitarAmp/actions/workflows/cmake.yml/badge.svg)](https://github.com/GuitarML/SmartGuitarAmp/actions/workflows/cmake.yml)

Guitar plugin made with JUCE that uses neural network models to emulate real world hardware.

See video demo on [YouTube](https://youtu.be/I9DElOaZvHos)

This plugin uses a WaveNet model to recreate the sound of real world hardware. The current version

models a small tube amp at clean and overdriven settings. Gain and EQ knobs were added to 

modulate the modeled sound.

![app](https://github.com/GuitarML/SmartGuitarAmp/blob/main/resources/amp_pic.jpg)

You can create your own models and load them in SmartGuitarAmp with minor code modifications.

To train your own models, use [PedalNetRT](https://github.com/GuitarML/PedalNetRT)

Model training is done using PyTorch on pre recorded .wav samples. More info in the above repository.

To share your best models, email the json files to [email protected] and they may be included 

in the latest release as a downloadable zip.

Also see companion plugin, the [SmartGuitarPedal](https://github.com/GuitarML/SmartGuitarPedal)


Note: As of SmartAmp version 1.3, the custom model load was removed to simplify the plugin. To load user

trained models, use the SmartGuitarPedal, which plays all models trained with PedalNetRT.

## Installing the plugin

1. Download the appropriate plugin installer (Windows, Mac, Linux) from the [Releases](https://github.com/GuitarML/SmartGuitarAmp/releases) page.

2. Run the installer and follow the instructions. May need to reboot to allow your DAW to recognize the new plugin.

## Build Instructions

### Build with Cmake

```bash

# Clone the repository

$ git clone https://github.com/GuitarML/SmartGuitarAmp.git

$ cd SmartGuitarAmp

# initialize and set up submodules

$ git submodule update --init --recursive

# build with CMake

$ cmake -Bbuild

$ cmake --build build --config Release

```

The binaries will be located in `SmartAmp/build/SmartAmp_artefacts/`

## License

This project is licensed under the Apache License, Version 2.0 - see the [LICENSE](LICENSE) file for details.

This project builds off the work done in [WaveNetVA](https://github.com/damskaggep/WaveNetVA)

The EQ code used in this plugin is based on the work done by Michael Gruhn in 4BandEQ algorithm.