rishikksh20/AudioMAE-pytorch

Unofficial PyTorch implementation of Masked Autoencoders that Listen

35
/ 100
Emerging

This is a PyTorch implementation of a Masked Autoencoder for audio. It takes audio spectrograms as input and learns to reconstruct them even after a large portion has been masked, producing a reconstructed spectrogram. It's intended for machine learning researchers and audio engineers working on self-supervised learning for audio.

No commits in the last 6 months.

Use this if you are a machine learning researcher or audio engineer looking to apply self-supervised learning techniques to audio data for tasks like speech recognition, sound event detection, or music analysis.

Not ideal if you need an out-of-the-box solution for audio processing or if you are not comfortable working with raw PyTorch models for deep learning research.

audio-processing speech-recognition sound-analysis machine-learning-research self-supervised-learning
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 9 / 25
Maturity 16 / 25
Community 10 / 25

How are scores calculated?

Stars

71

Forks

6

Language

Python

License

MIT

Last pushed

Aug 08, 2022

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/rishikksh20/AudioMAE-pytorch"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.