etzinis/sudo_rm_rf
Code for SuDoRm-Rf networks for efficient audio source separation. SuDoRm-Rf stands for SUccessive DOwnsampling and Resampling of Multi-Resolution Features which enables a more efficient way of separating sources from mixtures.
This project helps audio engineers, researchers, and sound designers cleanly separate individual sounds from a mixed audio file. You input a recording with multiple overlapping sounds, and it outputs the separated individual sound components. This tool is designed for anyone working with audio who needs to isolate specific voices or environmental sounds efficiently without requiring powerful computing resources.
335 stars. No commits in the last 6 months.
Use this if you need to separate speech or environmental sounds from a complex audio mixture, especially if you want a balance of high performance and efficient use of computing power and memory.
Not ideal if your primary concern is absolute state-of-the-art separation performance at any computational cost, rather than resource efficiency.
Stars
335
Forks
36
Language
Jupyter Notebook
License
MIT
Category
Last pushed
Jul 06, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/etzinis/sudo_rm_rf"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
pytorch/audio
Data manipulation and transformation for audio signal processing, powered by PyTorch
asteroid-team/asteroid
The PyTorch-based audio source separation toolkit for researchers
deezer/spleeter
Deezer source separation library including pretrained models.
audeering/opensmile
The Munich Open-Source Large-Scale Multimedia Feature Extractor
audeering/opensmile-python
Python package for openSMILE