The MossFormer2_SS_16K model weights for 16 kHz speech separation in ClearerVoice-Studio 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.
Inference Providers
NEW
This model is not currently available via any of the supported third-party Inference Providers, and
HF Inference API was unable to determine this model's library.