Modelpublic

saattrupdan/wav2vec2-xls-r-300m-ftspeech

sourceHugging Faceotherupdated 3y agoView on Hugging Face

0likes918kdownloads

Model Card

XLS-R-300m-FTSpeech

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.

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

The use of this model needs to adhere to this license from the Danish Parliament.