XLS-R-300m-FTSpeech
Model description
This model is a fine-tuned version of facebook/wav2vec2-xls-r-300m on the FTSpeech dataset, being a dataset of 1,800 hours of transcribed speeches from the Danish parliament.
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 | 20.48 | 17.91 |
| Alvenir test set | 15.46 | 13.84 |
License
The use of this model needs to adhere to this license from the Danish Parliament.
- Downloads last month
- 29,512
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.
Model tree for saattrupdan/wav2vec2-xls-r-300m-ftspeech
Base model
facebook/wav2vec2-xls-r-300mEvaluation results
- wer on Danish Common Voice 8.0self-reported17.910
- wer on Alvenir ASR test datasetself-reported13.840