Rikorose/DeepFilterNet
Noise supression using deep filtering
Processes full-band audio at 48kHz with a lightweight deep filtering architecture optimized for real-time inference on embedded devices. Available as a standalone Rust binary (`deep-filter`), PyTorch-based Python package, and LADSPA plugin for PipeWire integration on Linux systems. Includes multi-frame filtering variants and pretrained models (DeepFilterNet, DeepFilterNet2, DeepFilterNet3) with optional postfiltering, supporting both CPU and GPU processing.
3,956 stars. Used by 1 other package. No commits in the last 6 months. Available on PyPI.
Stars
3,956
Forks
424
Language
Python
License
—
Category
Last pushed
Oct 17, 2024
Commits (30d)
0
Dependencies
7
Reverse dependents
1
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/Rikorose/DeepFilterNet"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related frameworks
iver56/audiomentations
A Python library for audio data augmentation. Useful for making audio ML models work well in the...
marl/openl3
OpenL3: Open-source deep audio and image embeddings
ductho-le/WaveDL
A Scalable Deep Learning Framework for Wave-Based Inverse Problems
Spijkervet/torchaudio-augmentations
Audio transformations library for PyTorch
torchsynth/torchsynth
A GPU-optional modular synthesizer in pytorch, 16200x faster than realtime, for audio ML researchers.