TS-9 guitar pedal clone using neural networks.

Overview

TS-M1N3

app

TS-M1N3 is a guitar plugin clone of the TS-9 Tubescreamer overdrive pedal. Machine learning was used to train a model of both the drive and tone knobs for an accurate recreation of the pedal in all possible configurations. This plugin uses two conditioned parameters during model training to recreate the entire device using machine learning, as opposed to snapshot models at a particular setting. For best results, use prior to amp -> cabinet -> reverb effects to fully simulate playing an overdrive pedal through a physical amplifier. This can be done with the NeuralPi plugin.

Check out a video demo on Youtube

Installing the plugin

  1. Download the appropriate plugin installer here (Windows, Mac)
  2. Run the installer and follow the instructions. May need to reboot to allow your DAW to recognize the new plugin.

Info

The Automated-GuitarAmpModelling project was used to train the .json models.
GuitarML maintains a fork with a few extra helpful features, including a Colab training script and wav file processing for conditioned parameters.

The plugin uses RTNeural, which is a highly optimized neural net inference engine intended for audio applications.

This plugin uses two json model files, one for 44.1kHz and one for 48kHz audio. The only difference is that the source training data is at the intended samplerate, 44.1kHz or 48kHz. Other samplerates can be used, but the sound may be distorted slightly.

For the training data, five steps for the gain and tone knobs were recorded (0.0, 0.25, 0.50, 0.75, 1.0), for a total of 25 output samples at 2 minutes each. An LSTM layer with a hidden size of 20 was used.

Build Instructions

Build with Cmake

# Clone the repository
$ git clone https://github.com/GuitarML/TS-M1N3.git
$ cd TS-M1N3

# 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 TS-M1N3/build/TS-M1N3_artefacts/

Build with Projucer

  1. Clone or download this repository.
  2. Download and install JUCE This project uses the "Projucer" application from the JUCE website.
  3. Initialize and set up submodules git submodule update --init --recursive
  4. Open the TS-M1N3.jucer file and in the appropriate Exporter Header Search Path field, enter the appropriate include paths from the modules folder. For example:
   <full-path-to>/TS-M1N3/modules/json/include
   <full-path-to>/TS-M1N3/modules/RTNeural
   <full-path-to>/TS-M1N3/modules/RTNeural/modules/xsimd/include
  1. Build TS-M1N3 from the Juce Projucer application.

Note: Make sure to build in Release mode unless actually debugging. Debug mode will not keep up with real time playing.

Special Thanks

Special thanks to the UAH (University of Alabama in Huntsville) MLAMSK Senior Design Team, whose research and hard work directly impacted the development of this plugin.

Issues
  • Implement real-time sample rate conversion

    Implement real-time sample rate conversion

    For this to work, I had to add a couple of submodules, so it might be necessary to git submodule update --init --recursive when in order to build with these changes.

    opened by jatinchowdhury18 2
Releases(v1.0.0)
Owner
Keith Bloemer
Anyone can get great guitar tone using modern computing technology. GuitarML is a community for advancing machine learning for use in electric guitar plugins.
Keith Bloemer
Tensors and Dynamic neural networks in Python with strong GPU acceleration

PyTorch is a Python package that provides two high-level features: Tensor computation (like NumPy) with strong GPU acceleration Deep neural networks b

null 52.5k Dec 1, 2021
A lightweight C library for artificial neural networks

Getting Started # acquire source code and compile git clone https://github.com/attractivechaos/kann cd kann; make # learn unsigned addition (30000 sam

Attractive Chaos 572 Nov 23, 2021
Convolutional Neural Networks

Darknet Darknet is an open source neural network framework written in C and CUDA. It is fast, easy to install, and supports CPU and GPU computation. D

Joseph Redmon 21.8k Dec 5, 2021
Low dependency(C++11 STL only), good portability, header-only, deep neural networks for embedded

LKYDeepNN LKYDeepNN 可訓練的深度類神經網路 (Deep Neural Network) 函式庫。 輕量,核心部份只依賴 C++11 標準函式庫,低相依性、好移植,方便在嵌入式系統上使用。 Class diagram 附有訓練視覺化 demo 程式 訓練視覺化程式以 OpenCV

Lin Kao-Yuan 34 Aug 13, 2021
Tiny CUDA Neural Networks

This is a small, self-contained framework for training and querying neural networks. Most notably, it contains a lightning fast "fully fused" multi-layer perceptron as well as support for various advanced input encodings, losses, and optimizers.

NVIDIA Research Projects 239 Dec 3, 2021
An Efficient Implementation of Analytic Mesh Algorithm for 3D Iso-surface Extraction from Neural Networks

AnalyticMesh Analytic Marching is an exact meshing solution from neural networks. Compared to standard methods, it completely avoids geometric and top

Jiabao Lei 31 Dec 7, 2021
An Efficient Implementation of Analytic Mesh Algorithm for 3D Iso-surface Extraction from Neural Networks

AnalyticMesh Analytic Marching is an exact meshing solution from neural networks. Compared to standard methods, it completely avoids geometric and top

null 29 Nov 5, 2021
A header-only C++ library for deep neural networks

MiniDNN MiniDNN is a C++ library that implements a number of popular deep neural network (DNN) models. It has a mini codebase but is fully functional

Yixuan Qiu 277 Nov 24, 2021
InsNet Runs Instance-dependent Neural Networks with Padding-free Dynamic Batching.

InsNet documentation InsNet (documentation) is a powerful neural network library aiming at building instance-dependent computation graphs. It is desig

Chauncey Wang 50 Nov 30, 2021
A framework for generic hybrid two-party computation and private inference with neural networks

MOTION2NX -- A Framework for Generic Hybrid Two-Party Computation and Private Inference with Neural Networks This software is an extension of the MOTI

ENCRYPTO 3 Nov 26, 2021
Grouped Feedback Delay Networks for Coupled Room Modeling

Grouped Feedback Delay Networks Reverb Plugin GFDNs connect multiple spaces with different T60 characteristics and a parameterized mixing matrix to co

Orchisama Das 20 Dec 1, 2021
Parallel library for approximate inference on discrete Bayesian networks

baylib C++ library Baylib is a parallel inference library for discrete Bayesian networks supporting approximate inference algorithms both in CPU and G

Massimiliano Pronesti 19 Nov 15, 2021
A GPU (CUDA) based Artificial Neural Network library

Updates - 05/10/2017: Added a new example The program "image_generator" is located in the "/src/examples" subdirectory and was submitted by Ben Bogart

Daniel Frenzel 89 Nov 20, 2021
simple neural network library in ANSI C

Genann Genann is a minimal, well-tested library for training and using feedforward artificial neural networks (ANN) in C. Its primary focus is on bein

Lewis Van Winkle 1.2k Nov 30, 2021
oneAPI Deep Neural Network Library (oneDNN)

oneAPI Deep Neural Network Library (oneDNN) This software was previously known as Intel(R) Math Kernel Library for Deep Neural Networks (Intel(R) MKL-

oneAPI-SRC 2.6k Dec 3, 2021
DyNet: The Dynamic Neural Network Toolkit

The Dynamic Neural Network Toolkit General Installation C++ Python Getting Started Citing Releases and Contributing General DyNet is a neural network

Chris Dyer's lab @ LTI/CMU 3.3k Nov 28, 2021
neural net with blackjack and hookers

SkyNet is a light deep learning library. Linux/Windows License ResNet cpp-example for Win Compare with Tensorflow, inference ResNet50. PC: i5-2400, GF

Alexander Medvedev 62 Oct 24, 2021
TensorVox is an application designed to enable user-friendly and lightweight neural speech synthesis in the desktop

TensorVox is an application designed to enable user-friendly and lightweight neural speech synthesis in the desktop, aimed at increasing accessibility to such technology.

null 114 Nov 23, 2021
Benchmark framework of compute-in-memory based accelerators for deep neural network (inference engine focused)

DNN+NeuroSim V1.3 The DNN+NeuroSim framework was developed by Prof. Shimeng Yu's group (Georgia Institute of Technology). The model is made publicly a

NeuroSim 17 Nov 29, 2021