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
- 1
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.
Evaluation results
- wer on Danish Common Voice 8.0self-reported40.540
- wer on Alvenir ASR test datasetself-reported40.660