# Multilingual pre-training fine-tuning

This model is a speech recognition model fine-tuned on the Common Voice Slovenian dataset based on facebook/wav2vec2-xls-r-300m, with a word error rate of 0.3271.

A Finnish automatic speech recognition model fine-tuned based on facebook/wav2vec2-xls-r-300m, trained with 275.6 hours of Finnish annotated data, supports use with KenLM language model.

An acoustic model fine-tuned for Finnish automatic speech recognition based on facebook/wav2vec2-xls-r-300m, trained with 275.6 hours of annotated Finnish speech data