---
license: apache-2.0
---

The MossFormer2_SS_16K model weights for 16 kHz speech separation in [ClearerVoice-Studio](https://github.com/modelscope/ClearerVoice-Studio/tree/main) repo.

This model is trained on large scale datasets inclduing open-sourced and private data.

It separates mixed-speaker speeches into individual speaker's speech.