# Requires fine-tuning

BERT model trained on German legal data, specialized in legal text processing

Wav2Vec2 base model pretrained on Portuguese VoxPopuli corpus, suitable for speech recognition tasks

A speech recognition base model pretrained on 100,000 hours of unannotated data from the VoxPopuli corpus

A speech recognition model pre-trained on 100,000 hours of unlabeled data from the VoxPopuli corpus, supporting multilingual speech representation learning

A general-purpose BERT-large model built from the extensive digital collections of the National Library of Norway, supporting Norwegian text processing.