This wav2vec2-base model has been pretrained on ~1300 hours of danish speech data. The pretraining data consists of podcasts and audiobooks and is unfortunately not public available. However, we were allowed to distribute the pretrained model.
This model was pretrained on 16kHz sampled speech audio. When using the model, make sure to use speech audio sampled at 16kHz.
The pre-training was done using the fairseq library in January 2021.
It needs to be fine-tuned to perform speech recognition.
- Downloads last month
Unable to determine this model’s pipeline type. Check the docs .