| license: cc-by-nc-sa-4.0 | |
| The checkpoint for [TSELM: Target Speaker Extractoion using Discrete Tokens and Language Models](https://github.com/Beilong-Tang/TSELM). | |
| It contains the checkpoint for Scalable HiFiGAN backend, kmeans model and TSELM-L model. Details can be found [here](https://github.com/Beilong-Tang/TSELM) |