Downloads · 30 days
4
31% of all-time downloads
jaeyeonkim99/BEATs-tokenizer-AS2M-iter1
BEATs-tokenizer-AS2M-iter1 is a machine learning model from jaeyeonkim99. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for espnet. The card lists the license as cc-by-4.0.
Acoustic VQ tokenizer (1024-entry codebook) trained on AudioSet-2M with ESPnet, following BEATs (Table 4). Distilled with the iteration-0 BEATs encoder as teacher; used to generate the discrete targets for iteration-1…
Downloads · 30 days
4
31% of all-time downloads
All-time downloads
13
Public
Repo size
367 MB
Likes
0
Public
Click a slice to open those files.
.pt367 MB · 100%
From the Hugging Face model README
Acoustic VQ tokenizer (1024-entry codebook) trained on AudioSet-2M with ESPnet,
following BEATs (Table 4). Distilled with the
iteration-0 BEATs encoder as teacher; used to generate the discrete targets for
iteration-1 encoder
pre-training. Produced by the egs2/audioset/ssl1 recipe (external_tokenizer_model).
@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}
}