SekiroRong/KAN-AutoEncoder
KAE : KAN-based AutoEncoder (AE, VAE, VQ-VAE, RVQ, etc.)
This tool helps researchers and engineers working with audio signals efficiently compress and reconstruct complex sound data. It takes raw audio sequences or other sinusoidal signals and outputs a much smaller, compressed representation that can be expanded back to the original with high fidelity. Anyone involved in audio processing, sound analysis, or signal compression could use this to improve data handling.
No commits in the last 6 months.
Use this if you need to significantly reduce the size of audio or similar signal data while maintaining high quality reconstruction, or if you want to experiment with mixing different audio signals efficiently.
Not ideal if your primary goal is general image processing or natural language understanding, as this tool is specifically designed for signals with sinusoidal characteristics.
Stars
39
Forks
2
Language
Jupyter Notebook
License
MIT
Last pushed
May 23, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/SekiroRong/KAN-AutoEncoder"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
Naresh1318/Adversarial_Autoencoder
A wizard's guide to Adversarial Autoencoders
mseitzer/pytorch-fid
Compute FID scores with PyTorch.
acids-ircam/RAVE
Official implementation of the RAVE model: a Realtime Audio Variational autoEncoder
ratschlab/aestetik
AESTETIK: Convolutional autoencoder for learning spot representations from spatial...
jaanli/variational-autoencoder
Variational autoencoder implemented in tensorflow and pytorch (including inverse autoregressive flow)