# sdatkinson/neural-amp-modeler

**Attribution required: if you use, quote, or summarise this content, you must credit and link back to [awesome-repositories.com](https://awesome-repositories.com/repository/sdatkinson-neural-amp-modeler).**

2,460 stars · 222 forks · Python · mit

## Links

- GitHub: https://github.com/sdatkinson/neural-amp-modeler
- awesome-repositories: https://awesome-repositories.com/repository/sdatkinson-neural-amp-modeler.md

## Description

Neural Amp Modeler is an open-source project that captures the tonal character of analog audio gear by training a neural network on paired dry and reamped audio recordings. It provides a complete pipeline for learning how a guitar amplifier, effects pedal, or other audio device transforms a signal, then exports the trained model into a portable file format for use in other applications.

The project centers on a file-format-based approach to model distribution, where each trained neural network is saved as a single .nam file that can be shared and loaded by different host applications. A real-time inference engine processes live audio streams with low-latency neural network forward passes, enabling the emulated device to be used in performance or recording contexts.

The training workflow uses a supervised learning approach, taking a dry input recording and a reamped output recording as paired training data to learn the device's transfer function. Once trained, the model weights and architecture are serialized into a compact, portable format that simplifies model management and swapping across different software environments.

## Tags

### Artificial Intelligence & ML

- [Audio Gear Model Trainers](https://awesome-repositories.com/f/artificial-intelligence-ml/audio-generation-models/audio-sample-reconstruction/audio-gear-model-trainers.md) — Trains neural networks from paired dry and reamped audio recordings to learn gear transformations. ([source](https://neural-amp-modeler.readthedocs.io))
- [Analog Gear Emulators](https://awesome-repositories.com/f/artificial-intelligence-ml/audio-tokenization/neural-audio-compression/analog-gear-emulators.md) — Trains neural networks to emulate the sound of guitar amplifiers and effects pedals.
- [Audio Transfer Function Learners](https://awesome-repositories.com/f/artificial-intelligence-ml/gan-training-loops/supervised-training-pipelines/audio-transfer-function-learners.md) — Provides a supervised training pipeline using paired dry and reamped audio recordings.
- [Audio Device Character Capturers](https://awesome-repositories.com/f/artificial-intelligence-ml/machine-learning/infrastructure/model-training-and-tuning/training-frameworks/model-training-pipelines/audio-language-model-training/audio-device-character-capturers.md) — Trains neural networks on paired input-output audio samples to capture audio device sonic character. ([source](https://neural-amp-modeler.readthedocs.io/model-file.html))
- [Audio Gear Response Modelers](https://awesome-repositories.com/f/artificial-intelligence-ml/machine-learning/infrastructure/model-training-and-tuning/training-frameworks/model-training-pipelines/audio-language-model-training/audio-gear-response-modelers.md) — Trains neural networks on paired DI and reamp audio to model guitar amplifier and effect responses. ([source](https://neural-amp-modeler.readthedocs.io/))
- [Neural Network Training](https://awesome-repositories.com/f/artificial-intelligence-ml/neural-network-training.md) — Trains neural networks on audio samples to replicate the tonal character of guitar amplifiers and effects. ([source](https://neural-amp-modeler.readthedocs.io/tutorials/main.html))
- [Neural Amp Model Runtimes](https://awesome-repositories.com/f/artificial-intelligence-ml/neural-networks/real-time-audio-filters/neural-amp-model-runtimes.md) — Loads serialized models and processes live audio streams with low-latency neural network inference.
- [Guitar Amp Modelers](https://awesome-repositories.com/f/artificial-intelligence-ml/training-instrumentation/neural-instrument-training-tools/guitar-amp-modelers.md) — Trains neural networks to capture the tonal character of guitar amplifiers and effects pedals. ([source](https://cdn.jsdelivr.net/gh/sdatkinson/neural-amp-modeler@main/README.md))
- [Model Export and Portability](https://awesome-repositories.com/f/artificial-intelligence-ml/machine-learning/infrastructure/machine-learning-training/fine-tuning-and-alignment/fine-tuning-frameworks/speech-model-fine-tuning/model-export-and-portability.md) — Exports trained neural networks into portable files that other applications can load and use. ([source](https://neural-amp-modeler.readthedocs.io))
- [Model Exporting](https://awesome-repositories.com/f/artificial-intelligence-ml/model-training/model-exporting.md) — Exports trained neural networks into file formats loadable by real-time playback plugins or standalone apps. ([source](https://neural-amp-modeler.readthedocs.io/api.html))
- [Functional Model Exports](https://awesome-repositories.com/f/artificial-intelligence-ml/model-weight-export-formats/functional-model-exports.md) — Exports trained neural networks into a file format designed for real-time playback in other applications. ([source](https://cdn.jsdelivr.net/gh/sdatkinson/neural-amp-modeler@main/README.md))

### Business & Productivity Software

- [Neural Amp Model Files](https://awesome-repositories.com/f/business-productivity-software/cross-platform-binary-distribution/model-binary-formats/neural-amp-model-files.md) — Ships a dedicated .nam file format for packaging trained neural amp models.

### Web Development

- [Model Serialization Formats](https://awesome-repositories.com/f/web-development/model-serializers/neural-network-binary-serialization/model-serialization-formats.md) — Serializes trained neural network weights and architecture into a portable file format.

### DevOps & Infrastructure

- [Model Export Formats](https://awesome-repositories.com/f/devops-infrastructure/deployment-management/model-export-formats.md) — Saves trained neural networks into a portable file format that other applications can load and use. ([source](https://neural-amp-modeler.readthedocs.io/_sources/index.rst.txt))

### Software Engineering & Architecture

- [Model Packaging](https://awesome-repositories.com/f/software-engineering-architecture/application-frameworks/single-file-backend-servers/single-file-executables/model-packaging.md) — Packages each trained neural network into a single self-contained file for simplified model management.