-
Hviske v2
Hviske v2 er en state of the art dansk transskriptionsmodel der er trænet af syv.ai. Modellen er gratis at bruge, men sørg for at være opmærksom på at brugen falder indenfor... -
CoRal - Danish Conversational and Read-aloud Dataset
CoRal is a comprehensive Automatic Speech Recognition (ASR) dataset designed to capture the diversity of the Danish language across various dialects, accents, genders, and age... -
Røst-315M
RØST-315M is a speech recognition model based on the CoRal-dataset, and the model is a product of the CoRal-project. CoRal is a project that aims to produce datasets that are...
Du kan også tilgå dette register med API (se API-dokumenter).