| license: apache-2.0 | |
| This model is trained on Vox2. It uses ECAPA-TDNN as teacher model. The speaker module is placed | |
| at the end of the encoder |
| license: apache-2.0 | |
| This model is trained on Vox2. It uses ECAPA-TDNN as teacher model. The speaker module is placed | |
| at the end of the encoder |