kkoutini/PaSST

Efficient Training of Audio Transformers with Patchout

46
/ 100
Emerging

This project helps machine learning engineers and researchers efficiently train audio transformers. It takes audio spectrograms as input and produces trained transformer models, along with significant reductions in training time and GPU memory. This is ideal for those developing and experimenting with audio classification, sound event detection, or other audio understanding tasks.

370 stars. No commits in the last 6 months.

Use this if you are developing transformer models for audio processing and need to drastically cut down on training time and GPU memory usage while maintaining or improving performance.

Not ideal if you are looking for a pre-built solution for immediate audio inference without needing to train or fine-tune models yourself.

audio-classification sound-event-detection audio-analysis machine-learning-research deep-learning-optimization
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 20 / 25

How are scores calculated?

Stars

370

Forks

58

Language

Python

License

Apache-2.0

Last pushed

Jan 12, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/kkoutini/PaSST"

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