sdatkinson/NeuralAmpModelerCore

Core DSP library for NAM plugins

What it solves

This library provides the core digital signal processing (DSP) logic required to run neural network-based amplifier models. It allows developers to integrate neural amplifier modeling into plugins or other audio software, providing a high-performance C++ implementation of the underlying neural networks.

How it works

The library uses C++ and the Eigen linear algebra library to execute the neural networks that define an amplifier's sonic characteristics. It includes tools for testing model loading (loadmodel) and measuring real-time performance (benchmodel) to ensure the efficiency of the neural network inference during audio processing.

Who it’s for

Audio software developers and plugin creators who want to implement neural amplifier modeling in their own applications.

Highlights

  • Core C++ DSP library for NAM plugins.
  • Includes a benchmodel tool to test real-time execution speed.
  • Includes a loadmodel tool to verify the model file loading process.
  • Uses Eigen for high-performance linear algebra routines.

Related

  • Project
    dmlc/dmlc-core

    A backbone C++ library that provides the essential building blocks for creating efficient and scalable distributed machine learning systems.

  • Project
    jatinchowdhury18/RTNeural

    A lightweight C++ neural network inferencing engine optimized for real-time systems and audio processing.

  • Project
    mikeoliphant/neural-amp-modeler-lv2

    An LV2 plugin for playing back neural network machine learning amplifier models using the NeuralAudio engine.

  • Project
    Artelnics/opennn

    A high-performance C++ library for implementing neural networks used in advanced analytics for business, healthcare, and engineering.

  • Project
    0xShug0/audio.cpp

    A high-performance C++ audio inference framework built on ggml that provides a portable, native runtime for running diverse local audio models including TTS, ASR, and voice conversion.