wav2vec2-xls-r-300m-ftspeech/README.md

language, license, datasets, metrics, tasks, base_model, model-index

language	license	datasets	metrics	tasks	base_model	model-index
da	other	ftspeech	wer	automatic-speech-recognition	facebook/wav2vec2-xls-r-300m	name results wav2vec2-xls-r-300m-ftspeech task dataset metrics type automatic-speech-recognition name type args Danish Common Voice 8.0 mozilla-foundation/common_voice_8_0 da type value wer 17.91 task dataset metrics type automatic-speech-recognition name type Alvenir ASR test dataset Alvenir/alvenir_asr_da_eval type value wer 13.84

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.