AppleHolic/source_separation
Deep learning based speech source separation using Pytorch
This project helps audio engineers and content creators separate individual speech and singing voices from mixed audio recordings. You feed it a sound file containing speech, music, and noise, and it outputs cleaner audio files with the speech or singing isolated. It's designed for anyone working with audio who needs to remove background noise or extract specific vocal elements.
319 stars. No commits in the last 6 months.
Use this if you need to cleanly extract human speech or a singing voice from an audio recording that contains other sounds.
Not ideal if you need to separate instrument tracks from each other, as it focuses specifically on vocal source separation.
Stars
319
Forks
47
Language
Jupyter Notebook
License
Apache-2.0
Category
Last pushed
Nov 20, 2020
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/AppleHolic/source_separation"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
iver56/audiomentations
A Python library for audio data augmentation. Useful for making audio ML models work well in the...
Rikorose/DeepFilterNet
Noise supression using deep filtering
torchsynth/torchsynth
A GPU-optional modular synthesizer in pytorch, 16200x faster than realtime, for audio ML researchers.
marl/openl3
OpenL3: Open-source deep audio and image embeddings
archinetai/audio-data-pytorch
A collection of useful audio datasets and transforms for PyTorch.