MiRA (Music Replication Assessment) tool is a model-independent open evaluation method based on four diverse audio music similarity metrics to assess exact data replication of the training set.

Official repository for the paper "Forging and Removing Latent-Noise Diffusion Watermarks Using a Single Image".

GRAFX: An Open-Source Library for Audio Processing Graphs in PyTorch

Differentiable dynamic range controller in PyTorch.

Banquet: A Stem-Agnostic Single-Decoder System for Music Source Separation Beyond Four Stems

A TTS model capable of generating ultra-realistic dialogue in one pass.

Variable Bitrate Residual Vector Quantization for Audio Coding

PyTorch implementation of DiffRoll, a diffusion-based generative automatic music transcription (AMT) model

Implementation of the paper "Variable Bitrate Residual Vector Quantization for Audio Coding"

[PyTorch] Minimal codebase for MusicGen models

Refactored / updated version of `stable-audio-tools` which is an open-source code for audio/music generative models originally by Stability AI.

Audio generation using diffusion models, in PyTorch.

A minimal Pytorch Implementation of Stochastically Quantized Variational AutoEncoder (SQ-VAE) by Sony