slseanwu/beats-conformer-bart-audio-captioner

Summary

This repo contains the config & pretrained weights of the model described in the following paper:

• Improving Audio Captioning Models with Fine-grained Audio Features, Text Embedding Supervision, and LLM Mix-up Augmentation
  Shih-Lun Wu, Xuankai Chang, Gordon Wichern, Jee-weon Jung, François Germain, Jonathan Le Roux, and Shinji Watanabe
  Int. Conf. on Acoustics, Speech, and Signal Processing (ICASSP) 2024
  [arXiv page]

GitHub Repository

To use this model, please refer to our code published at:

• https://github.com/slSeanWU/beats-conformer-bart-audio-captioner

Training Data

• Pretrain
  • AudioCaps: https://github.com/cdjkim/audiocaps/tree/master
  • ChatGPT mix-ups from Clotho: https://huggingface.co/datasets/slseanwu/clotho-chatgpt-mixup-50K
• Finetune
  • Clotho (V2): https://zenodo.org/records/4783391

BibTex

If you find our model useful, please consider citing our paper. Thanks!

@inproceedings{wu2024improving,
  title={Improving Audio Captioning Models with Fine-grained Audio Features, Text Embedding Supervision, and LLM Mix-up Augmentation},
  author={Wu, Shih-Lun and Chang, Xuankai and Wichern, Gordon and Jung, Jee-weon and Germain, Fran{\c{c}}ois and Le Roux, Jonathan and Watanabe, Shinji},
  booktitle={Proc. Int. Conf. on Acoustics, Speech and Signal Processing (ICASSP)},
  year={2024}
}