WavLMMSDD
PublicThis repository combines `WavLM`, a powerful speech representation model from Microsoft, with `MSDD` (Multi-Scale Diarization Decoder), a state-of-the-art approach for speaker diarization from Nvidia.
Creat:2025-02-14T22:03:51
Update:2025-03-15T20:57:23
7
Stars
0
Stars Increase