https://github.com/guitarml/chameleon
Vintage guitar amp using neural networks.
https://github.com/guitarml/chameleon
audio guitar juce-framework machinelearning neural-network
Last synced: about 1 year ago
JSON representation
Vintage guitar amp using neural networks.
- Host: GitHub
- URL: https://github.com/guitarml/chameleon
- Owner: GuitarML
- License: gpl-3.0
- Created: 2021-03-26T20:28:37.000Z (about 5 years ago)
- Default Branch: main
- Last Pushed: 2023-01-05T14:57:09.000Z (over 3 years ago)
- Last Synced: 2025-03-21T01:11:08.375Z (over 1 year ago)
- Topics: audio, guitar, juce-framework, machinelearning, neural-network
- Language: C++
- Homepage: https://guitarml.com/
- Size: 1.78 MB
- Stars: 83
- Watchers: 4
- Forks: 4
- Open Issues: 1
-
Metadata Files:
- Readme: README.md
- Funding: .github/FUNDING.yml
- License: LICENSE.txt
Awesome Lists containing this project
README
# Chameleon
[](https://github.com/GuitarML/Chameleon/actions/workflows/cmake.yml) [](https://www.gnu.org/licenses/gpl-3.0) [](https://somsubhra.github.io/github-release-stats/?username=GuitarML&repository=Chameleon&page=1&per_page=30)
Chameleon is a guitar plugin using neural networks to create three distinct sounds from a vintage style amp head. EQ and gain were added to
allow further modification of the three core sounds, named Red (high gain), Gold (crunchy), and Green (crisp and clean). In the same
way a real amp head is used with a cabinet and other effects, this plugin is intended to be used in the signal chain along with IR's (cab sim),
reverb, and any number of guitar effects.
Chameleon's core sound comes from a neural net inference engine which allows the plugin to disguise itself as a high end
tube amplifier. The engine uses a stateful LSTM model, which improves the sound quality of the previous stateless LSTM used in the SmartAmpPro. It
also improves CPU usage compared to the [SmartAmpPro](https://github.com/GuitarML/SmartAmpPro) and [SmartGuitarAmp](https://github.com/GuitarML/SmartGuitarAmp).
Check out sound demos on YouTube: [Heavy Demo](https://youtu.be/1oYiklGes6A), [Funky Demo](https://youtu.be/kXecJX9kWpQ)
Check out the tech article on [Towards Data Science](https://towardsdatascience.com/neural-networks-for-real-time-audio-stateful-lstm-b534babeae5d)
Chameleon is part of the [2021 KVR Audio Developer Challenge](https://www.kvraudio.com/product/chameleon-by-guitarml)
## Installing the plugin
1. Download the appropriate plugin installer (Windows, Mac, Linux) from the [Releases](https://github.com/GuitarML/Chameleon/releases) page.
2. Run the installer and follow the instructions. May need to reboot to allow your DAW to recognize the new plugin.
## Info
Re-creation of the LSTM inference model from [Real-Time Guitar Amplifier Emulation with Deep
Learning](https://www.mdpi.com/2076-3417/10/3/766/htm)
The [Automated-GuitarAmpModelling](https://github.com/Alec-Wright/Automated-GuitarAmpModelling) project was used to train the .json models.
GuitarML maintains a [fork](https://github.com/GuitarML/Automated-GuitarAmpModelling) with a few extra helpful features, including a Colab training script.
The plugin uses [RTNeural](https://github.com/jatinchowdhury18/RTNeural), which is a highly optimized neural net inference engine intended for audio applications.
## Build Instructions
### Build with Cmake
```bash
# Clone the repository
$ git clone https://github.com/GuitarML/Chameleon.git
$ cd Chameleon
# 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 `Chameleon/build/Chameleon_artefacts/`