tatsu1020 / self-supervised-dutch-dysarthria-asr Goto Github PK
View Code? Open in Web Editor NEWThis is a repository presenting the outcome of my thesis for MSc. Voice Technology at the University of Groningen. The research developed the Dutch dysarthric speech recognition with self-supervised learning (SSL) models, wav2vec 2.0 and XLSR-53. The repo contains the fine-tuned models and the evaluation dataset.
License: MIT License