Stars
Repository for training models for music source separation.
Audio production style transfer with inference-time opt 10000 imization
Multitrack music mixing style transfer given a reference song using differentiable mixing console.
Framework for differentiable black-box and gray-box audio effects modeling
Implementation of Differentiable Digital Signal Processing (DDSP) in Pytorch
Fine-tune Stable Audio Open with DiT ControlNet.
Generative models for conditional audio generation
Community list of startups working with AI in audio and music technology
Stable-V2A: Synthesis of Synchronized Sound Effect with Temporal and Semantic Controls
Encode and decode audio samples to/from compressed latent representations!
Self-supervised learning for fast pitch estimation
Dataset of dry/wet pairs for audio effects research
The calflops is designed to calculate FLOPs、MACs and Parameters in all various neural networks, such as Linear、 CNN、 RNN、 GCN、Transformer(Bert、LlaMA etc Large Language Model)
a better documented version of webMUSHRA
Important papers and associated code on automatic mixing research
Differentiable audio signal processors in PyTorch
GRAFX: An Open-Source Library for Audio Processing Graphs in PyTorch
Phaser experiments source code for "Differentiable All-pole Filters for Time-varying Audio Systems".
SyncFusion: Multimodal Onset-synchronized Video-to-Audio Foley Synthesis
Rational Activation Functions - Replacing Padé Activation Units
On-going VA modeling research. Modeling dynamic range compressor using S4.
A lightweight library for Frechet Audio Distance calculation.