Torsion-Audio/nn-inference-template
Neural network inference template for real-time cricital audio environments - presented at ADC23
This project helps DSP engineers and audio developers integrate neural network models into real-time audio applications like VSTs or standalone effects. It takes pre-trained neural network models and real-time audio signals as input, producing audio signals processed by the neural network with guaranteed real-time performance. This is ideal for audio plugin developers or embedded audio system designers.
130 stars. No commits in the last 6 months.
Use this if you need a reliable, real-time-safe way to embed neural network inference directly into your audio processing plugins or applications.
Not ideal if you are looking for a pre-built audio effect or a tool for offline audio processing or sound design without real-time performance constraints.
Stars
130
Forks
6
Language
C++
License
MIT
Category
Last pushed
Jul 28, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/Torsion-Audio/nn-inference-template"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
iver56/audiomentations
A Python library for audio data augmentation. Useful for making audio ML models work well in the...
Rikorose/DeepFilterNet
Noise supression using deep filtering
torchsynth/torchsynth
A GPU-optional modular synthesizer in pytorch, 16200x faster than realtime, for audio ML researchers.
marl/openl3
OpenL3: Open-source deep audio and image embeddings
archinetai/audio-data-pytorch
A collection of useful audio datasets and transforms for PyTorch.