GitHub topics: speech-embedding
bunyaminergen/WavLMMSDD
This 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.
Language: Jupyter Notebook - Size: 1.8 MB - Last synced at: 28 days ago - Pushed at: 4 months ago - Stars: 7 - Forks: 3
DigitalPhonetics/BetterFinetuning
Code accompanying our paper on finetuning self-supervised general speech representations with a combination of contrastive and non-contrastive methods.
Language: Python - Size: 75.2 KB - Last synced at: 3 months ago - Pushed at: almost 3 years ago - Stars: 1 - Forks: 0
