Stars
Accompanying repository for the paper "Automatic Music Mixing Using a Generative Model of Effect Embeddings"
Style transfer of synthetic electric guitar to more realistic electric guitar audio using flow matching.
An enhanced version of All-In-One with integrated source separation and modern PyTorch compatibility
Production-ready, unified inference toolkit for the MT3 music transcription model family
Real-time end-to-end singing voice conversion system based on DDSP (Differentiable Digital Signal Processing)
Joint Embedding Predictive Architecture for Musical Stem Compatibility Estimation
A Python library for audio data augmentation. Useful for making audio ML models work well in the real world, not just in the lab.
Easy to use stem (e.g. instrumental/vocals) separation from CLI or as a python package, using a variety of amazing pre-trained models (primarily from UVR)
Fast audio data augmentation in PyTorch. Inspired by audiomentations. Useful for deep learning.
Encode and decode audio samples to/from continuous and discrete compressed representations!
A Large Dataset of Paired Guitar Audio Recordings and Tablatures
Unified automatic quality assessment for speech, music, and sound.
Official implementation of WildFX Dataset Generating pipeline.
Object-oriented handling of audio data, with GPU-powered augmentations, and more.
Implementation of 1D, 2D, and 3D FFT convolutions in PyTorch. Much faster than direct convolutions for large kernel sizes.
"Fx-Encoder++: Extracting Instrument-wise Audio Effect Representations from Mixtures"
Implementation of the paper "ITO-Master: Inference-Time Optimization for Audio Effects Modeling of Music Mastering Processors"
Accompanying repository for the paper "DiffVox: A Differentiable Model for Capturing and Analysing Professional Effects Distributions"
FxNorm-Automix - Implementation of automatic music mixing systems. We show how we can use wet music data and repurpose it to train a fully automatic mixing system
Model Compression Toolkit (MCT) is an open source project for neural network model optimization under efficient, constrained hardware. This project provides researchers, developers, and engineers a…
A collection of LTSpice simulation files for popular guitar effects. 🎸 🎵 📈 Pull requests welcome 😃
Training code for FAcodec presented in NaturalSpeech3
Kimi-Audio, an open-source audio foundation model excelling in audio understanding, generation, and conversation
a list of demo websites for automatic music generation research
A GPU accelerated and torch based audio DSP library