File size: 359 Bytes
59fb133 |
1 2 3 4 5 6 7 8 9 |
---
license: apache-2.0
---
The AV_MossFormer2_TSE_16K model weights for 16 kHz audio-visual target speaker extraction in [ClearerVoice-Studio](https://github.com/modelscope/ClearerVoice-Studio/tree/main) repo.
This model is trained on large scale open-sourced datasets.
It extracts each speaker's voice from a multi-speaker video using facial recognition. |