This model is a fine-tuned version of facebook/wav2vec2-xls-r-300m on the Common Voice 8 dataset.
Note; during training test set was used as validation set, so this model could have problems with generalisation.
Model license: MIT License.
HuggingFace link: robinhad/wav2vec2-xls-r-300m-uk
Metrics
Loss: 0.4165
Wer: 27,99%
Cer: 6,01%