Tino3141/blap

This work is based on our paper:

@INPROCEEDINGS{10887618,
  author={Lanzendörfer, Luca A. and Pinkl, Constantin and Perraudin, Nathanaël and Wattenhofer, Roger},
  booktitle={ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},
  title={Bootstrapping Language-Audio Pre-training for Music Captioning},
  year={2025},
  pages={1-5},
  keywords={Measurement; Large language models; Computational modeling; Signal processing; Transformers; Data models; Acoustics; Multiple signal classification; Speech processing; Music Captioning; Language Models; Contrastive Language-Audio Pre-training},
  doi={10.1109/ICASSP49660.2025.10887618}
}