README.md

metadata

language:
  - da
license: apache-2.0
tasks:
  - automatic-speech-recognition
datasets:
  - common_voice_8_0
metrics:
  - wer
model-index:
  - name: wav2vec2-xls-r-300m-cv8-da
    results:
      - task:
          type: automatic-speech-recognition
        dataset:
          type: mozilla-foundation/common_voice_8_0
          args: da
          name: Danish Common Voice 8.0
        metrics:
          - type: wer
            value: 26.45
      - task:
          type: automatic-speech-recognition
        dataset:
          type: Alvenir/alvenir_asr_da_eval
          name: Alvenir ASR test dataset
        metrics:
          - type: wer
            value: 25.8

XLS-R-300m-CV8-da

Model description

This model is a fine-tuned version of the multilingual acoustic model facebook/wav2vec2-xls-r-300m 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	31.33	26.45
Alvenir test set	30.54	25.80