hugofloresgarcia/vampnet

music generation with masked transformers!

45
/ 100
Emerging

Implements iterative audio generation through masked token prediction on discretized audio codes, using a coarse-to-fine two-stage architecture for progressive refinement. Supports fine-tuning on custom audio datasets, model export to HuggingFace, and integrates with Max/MSP via the Unloop plugin for real-time interactive music generation. Uses audiotools for audio I/O and argbind for configuration management across training, inference, and deployment workflows.

351 stars. No commits in the last 6 months.

Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 17 / 25

How are scores calculated?

Stars

351

Forks

42

Language

Max

License

MIT

Last pushed

May 16, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/hugofloresgarcia/vampnet"

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