ESPnet
audio
self-supervised-learning
beats

BEATs base encoder โ€” AudioSet-2M, iteration 0

BEATs base audio encoder pre-trained on AudioSet-2M with ESPnet, reproducing BEATs (Table 4). Iteration 0 is trained against random-projection targets. Produced by the egs2/audioset/ssl1 recipe.

Usage

Load into an ESPnet downstream classification recipe (e.g. egs2/esc50/asr1, egs2/as20k/cls1) via beats_ckpt_path:

encoder: beats
encoder_conf:
    beats_ckpt_path: beats_encoder_iter0.pt
    fbank_mean: 15.66439
    fbank_std: 6.38312

Downstream results

AS-20K test mAP ESC-50 (5-fold acc)
iter 0 29.72 93.35

Citation

@inproceedings{chen2022beats,
  title={BEATs: Audio Pre-Training with Acoustic Tokenizers},
  author={Chen, Sanyuan and Wu, Yu and Wang, Chengyi and Liu, Shujie and
          Tompkins, Daniel and Chen, Zhuo and Wei, Furu},
  booktitle={ICML}, year={2023}
}
@inproceedings{bharadwaj2025openbeats,
  title={OpenBEATs: A Fully Open-Source General-Purpose Audio Encoder},
  author={Bharadwaj, Shikhar and Cornell, Samuele and Choi, Kwanghee and
          Fukayama, Satoru and Shim, Hye-jin and Deshmukh, Soham and Watanabe, Shinji},
  booktitle={WASPAA}, year={2025}
}
Downloads last month
6
Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support

Paper for jaeyeonkim99/BEATs-base-AS2M-iter0