Central hub for RealtimeSanitizer and its associated tooling

Multitrack music mixing style transfer given a reference song using differentiable mixing console.

Fast audio data augmentation in PyTorch. Inspired by audiomentations. Useful for deep learning.

Model Fusion via Optimal Transport, NeurIPS 2020

Encode and decode audio samples to/from compressed latent representations!

On-going VA modeling research. Modeling dynamic range compressor using S4.

A Library for Differentiable Logic Gate Networks

An efficient pytorch implementation of selective scan in one file, works with both cpu and gpu, with corresponding mathematical derivation. It is probably the code which is the most close to select…

Modified Mamba code to run on CPU

Inference of Mamba models in pure C

Implementation of mamba with rust

Mamba SSM architecture

A simple and efficient Mamba implementation in pure PyTorch and MLX.

Vector (and Scalar) Quantization, in Pytorch

Installs Vivado on M1/M2/M3 macs

AQUA-Tk = Audio QUality Assessment-Toolkit. (In development)

Neural network inference template for real-time cricital audio environments - presented at ADC23

Self-supervised learning for fast pitch estimation

Virtual machines for iOS and macOS

Generative models for conditional audio generation

Official implementation of "Separate Anything You Describe"

DiffWave is a fast, high-quality neural vocoder and waveform synthesizer.

📝 Markdown code for lots of small badges 🎀 📌 (shields.io, forthebadge.com etc) 😎. Contributions are welcome! Please add yours!

🤗 Diffusers: State-of-the-art diffusion models for image and audio generation in PyTorch and FLAX.

Synthesis of percussion sounds using sinusoidal modelling, DDSP noise synthesis, and a neural source filter approach.