Skip to content

Source code for "Self-Supervised Representation Learning with a JEPA Framework for Multi-Instrument Music Transcription"

License

Notifications You must be signed in to change notification settings

marypilataki/amt-jepa

Repository files navigation

amt-jepa

Source code for the JEPA models used in "Self-Supervised Representation Learning with a JEPA Framework for Multi-Instrument Music Transcription" (WASPAA 2025).

MIAMT-JEPA framework

Usage

This repository builds on top the original i-JEPA codebase. This can be found here.

  • Pretrain a JEPA model on unlabeled data:
python main_baseline.py --config configs/mir_jepa_pretrain.yaml --devices cuda:0
  • Finetune a JEPA model on labeled data:
python main_finetune_baseline.py --config configs/mir_jepa_finetune.yaml --devices cuda:0
  • Train the transcriber probe on frozen JEPA features:
python main_transcriber.py --config configs/mir_jepa_transcriber.yaml --devices cuda:0

About

Source code for "Self-Supervised Representation Learning with a JEPA Framework for Multi-Instrument Music Transcription"

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages