The AV_MossFormer2_TSE_16K model weights for 16 kHz audio-visual target speaker extraction in ClearerVoice-Studio 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.
Inference Providers
NEW
This model is not currently available via any of the supported Inference Providers.
The model cannot be deployed to the HF Inference API:
The model has no library tag.