Lists (8)
Audio Generation
This includes trending, useful, and popular repositories for audio generation (diffusion models, etc.)Awesome Papers
Repos with Awesome Lists and Reading materialContinual & Incremental Learning
Repositories that implement techniques for continual, incremental, and life-long learning in Pytorch.Datasets
Mostly Symbolic Music DatasetsInteresting Graph-Based
This list contains interesting repos that implement graph-based techniques.ISMIR 2022
repos from ISMIR 2022 Bangaluru IndiaLLMs
The most notable and interesting LLM projects.Useful
A list of repositories with cool and useful information.Stars
Python tool for converting files and office documents to Markdown.
FINALLY: Fast and universal speech enhancement model delivering studio-quality audio for a wide range of recordings.
Python package that provides comprehensive tools for working with symbolic modern and mensural notations in Humdrum format. kernpy is a fully open-source project open to contributions.
Models and datasets for training deep learning automatic mixing models
Model Implementations, Evaluation Scripts, etc. for Music Source Restoration Challenge 2025.
A Dataset for Cover Song Identification and Understanding
A Large Dataset of Paired Guitar Audio Recordings and Tablatures
Official Python toolkit for the Qwen3-ASR API. Parallel high‑throughput calls, robust long‑audio transcription, multi‑sample‑rate support.
Encode and decode audio samples to/from continuous and discrete compressed representations!
Self-supervised key estimation model that matches performance with supervised state-of-the-art model.
Implementation of HS-TasNet, "Real-time Low-latency Music Source Separation using Hybrid Spectrogram-TasNet"
This toolbox aims to unify audio generation model evaluation for easier comparison.
SonicMaster: Towards Controllable All-in-One Music Restoration and Mastering
This is the official repository for M2UGen
Reference PyTorch implementation and models for DINOv3
MCP sever for controlling Elektron devices using LLMs
ACE-Step: A Step Towards Music Generation Foundation Model
A two-stage U-Net for high-fidelity denoising of historical recordings
Noise supression using deep filtering
PyTorch implementation of the Perceptual Evaluation of Speech Quality for wideband audio
Repository accompanying the paper 'GlobalMood: A cross-cultural benchmark for music emotion recognition'
A repository for the files of the MNExplainer tool designed to produce counterfactual explanations for symbolic music analysis GNN models.
MuseControlLite: Multifunctional Music Generation with Lightweight Conditioners [ICML 2025]
A curated list of Datasets, Models and Papers for Music Emotion Recognition (MER)
Implementation of Denoising Diffusion Probabilistic Model in Pytorch