VoxPopuli-Wav2vec2-large-CV8-da
Model description
This model is a fine-tuned version of the Swedish acoustic model facebook/wav2vec2-large-sv-voxpopuli on the Danish part of Common Voice 8.0, containing ~6 crowdsourced hours of read-aloud Danish speech.
Performance
The model achieves the following WER scores (lower is better):
Dataset | WER without LM | WER with 5-gram LM |
---|---|---|
Danish part of Common Voice 8.0 | 48.04 | 40.54 |
Alvenir test set | 48.43 | 40.66 |
- Downloads last month
- 6
Evaluation results
- wer on Danish Common Voice 8.0self-reported40.540
- wer on Alvenir ASR test datasetself-reported40.660