High-throughput tensor loading for PyTorch

Code for the paper “Automatic Music Sample Identification with Multi-Track Contrastive Learning”.

Official Repository of Smule Renaissance, Smule's Vocal Restoration Models

Official Implementation for NorMuon paper

Code for the blog "Neural audio codecs: how to get audio into LLMs"

PyTriton is a Flask/FastAPI-like interface that simplifies Triton's deployment in Python environments.

Encode and decode audio samples to/from continuous and discrete compressed representations!

PyTorch native post-training library

Audio-to-Audio Schrodinger Bridges is a diffusion-based audio restoration model for bandwidth extension and inpainting.

ARCH: Audio Representations benCHmark

JamendoMaxCaps is a large-scale dataset of 362,000 instrumental creative commons tracks

This is the M-AILABS Speech Dataset

Personalized Image Generation with Large Multimodal Models

Explore and interpret large embeddings in your browser with interactive visualization! 📍

Symbolic Music NLP Artificial Intelligence Toolkit

Frontier Open-Source Text-to-Speech

Community-maintained faiss wheel builder

🚀🚀 Efficient implementations of Native Sparse Attention

Chordonomicon: A Dataset of 666,000 Chord Progressions

Efficient Training of Audio Transformers with Patchout

Official implementation of the paper - GD-Retriever: Controllable generative text-music retrieval with diffusion models (Accepted at ISMIR25!)

MeanAudio: Fast and Faithful Text-to-Audio Generation with Mean Flows

Explorations into NEAT and some of its derivative research

Dual Diffusion is a generative diffusion model for music trained on video game soundtracks.

Fine-tune ModernBERT on a large Dataset with Custom Tokenizer Training

Open exchange format for DAWs