Source code for training models and using the hyperbolic interface proposed in our ICASSP 2023 paper, “Hyperbolic Audio Source Separation.”
☆73Apr 27, 2023Updated 3 years ago
Alternatives and similar repositories for hyper-unmix
Users that are interested in hyper-unmix are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Enhanced Reverberation As Supervision (ERAS) for unsupervised reverberant speech separation☆15Aug 1, 2024Updated 2 years ago
- PyTorch implementation of "Source Separation by Flow Matching (FLOSS)" by Google DeepMind☆98Nov 24, 2025Updated 10 months ago
- ☆23Jun 13, 2023Updated 3 years ago
- PodcastMix A dataset for separating music and speech in podcasts.☆44Aug 20, 2024Updated 2 years ago
- ☆16Sep 7, 2022Updated 4 years ago
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- Kymatio: Deep Learning meets Wavelet Theory for Music Signal Processing☆15Oct 27, 2025Updated 10 months ago
- ☆23Aug 30, 2022Updated 4 years ago
- Variations of L1 SNR Loss function for training audio source separation machine learning models☆45Sep 1, 2026Updated 3 weeks ago
- Differentiable audio signal processors in PyTorch☆301Dec 4, 2023Updated 2 years ago
- A fast implementation of bss_eval metrics for blind source separation☆150Mar 11, 2026Updated 6 months ago
- Moises Source Separation Public Dataset☆194Feb 5, 2025Updated last year
- Baseline multi-resolution cross network model trained using the Divide and Remaster Dataset☆89Jan 25, 2024Updated 2 years ago
- Unofficial PyTorch implementation of Differentiable Wavetable Synthesis by Shan et al., ICASSP 2022.☆45Feb 2, 2022Updated 4 years ago
- Transformer with Local Modeling by Convolution for Speech Separation and Enhancement☆136Aug 8, 2025Updated last year
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- Tutorial covering Open Source tools for Source Separation.☆15Nov 12, 2021Updated 4 years ago
- Source Separation training codebase for the Sound Demixing Challenge 2023.☆45May 18, 2023Updated 3 years ago
- Official implementation of EfficientLEAF, a learnable audio frontend.☆53Dec 9, 2022Updated 3 years ago
- Rearrange a music recording to match a new duration - Code for "Music Rearrangement Using Hierarchical Segmentation", ICASSP 2023☆46Jun 28, 2026Updated 2 months ago
- Multipurpose Multi Speaker Mixture Signal Generator☆48Feb 6, 2025Updated last year
- An official implementation of the ICASSP 2024 paper: Dual-Path TFC-TDF UNet for Music Source Separation☆113Mar 19, 2024Updated 2 years ago
- Demucs Lightning: A PyTorch lightning version of Demucs with Hydra and Tensorboard features☆85May 3, 2023Updated 3 years ago
- Single channel speech source separation by diffusion process (ICASSP 2023)☆127Mar 15, 2024Updated 2 years ago
- Landing Page for Divide and Remaster v3☆27Jul 29, 2025Updated last year
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- Ultra-low-bitrate Speech Codec for Speech Language Modeling Applications☆92Dec 20, 2024Updated last year
- MUSDB25 - A Fully Multitrack Dataset for Music Source Separation☆13Mar 29, 2025Updated last year
- End-to-end beat and downbeat tracking in the time domain.☆126Nov 10, 2021Updated 4 years ago
- A PyTorch Dataset for Slakh2100☆10Feb 14, 2024Updated 2 years ago
- ☆70Nov 6, 2023Updated 2 years ago
- Official repo for task-aware unified source separation (TUSS)☆25Jul 31, 2025Updated last year
- Frechet Audio Distance evaluation in PyTorch☆36Jun 9, 2023Updated 3 years ago
- Official Repository for "Training-Free Multi-Step Audio Source Separation"☆54May 26, 2025Updated last year
- code for "BEAT-ALIGNED SPECTROGRAM-TO-SEQUENCE GENERATION OF RHYTHM-GAME CHARTS" (ISMIR 2023 LBD)☆24Jan 29, 2024Updated 2 years ago
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- Music onset detector from Dance Dance Convolution packaged as a lightweight PyTorch module☆43Sep 22, 2023Updated 3 years ago
- Accompanying code for our paper "Point Cloud Audio Processing"☆18Jul 1, 2021Updated 5 years ago
- Accompanying code for our paper "Optimizing Short-Time Fourier Transform Parameters via Gradient Descent"☆33Oct 30, 2020Updated 5 years ago
- million song dataset split for extended clean tag & artist-level stratified☆52Aug 12, 2023Updated 3 years ago
- ☆32Sep 5, 2024Updated 2 years ago
- This repo hosts the code and model of "Separate What You Describe: Language-Queried Audio Source Separation", Interspeech 2022☆145Oct 11, 2023Updated 2 years ago
- General Purpose Audio Effect Removal☆116Aug 31, 2023Updated 3 years ago