# XLS-R architecture optimization

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 Bengali automatic speech recognition model fine-tuned from facebook/wav2vec2-xls-r-300m, trained on the OpenSLR_SLR53 dataset

This is an automatic speech recognition model fine-tuned on Latvian datasets based on facebook/wav2vec2-xls-r-300m, achieving a WER of 16.98% on the Common Voice 7 test set.

Turkish automatic speech recognition model fine-tuned based on facebook/wav2vec2-xls-r-300m

This is an automatic speech recognition model fine-tuned on the Punjabi (India) dataset based on the facebook/wav2vec2-xls-r-300m model.

A Romanian speech recognition model fine-tuned based on facebook/wav2vec2-xls-r-300m, achieving a WER of 12.46% on the Common Voice Romanian test set

This is an automatic speech recognition (ASR) model fine-tuned on the Upper Sorbian (HSB) dataset based on Facebook's wav2vec2-xls-r-300m model.

An automatic speech recognition model fine-tuned on the Upper Sorbian (hsb) dataset based on facebook/wav2vec2-xls-r-300m

This is an automatic speech recognition (ASR) model fine-tuned on Bulgarian speech datasets based on the facebook/wav2vec2-xls-r-300m model.

An automatic speech recognition model fine-tuned on the Assamese (Common Voice 8.0) dataset based on facebook/wav2vec2-xls-r-300m

This model is an automatic speech recognition (ASR) model fine-tuned on the Erzya language (MYV) dataset based on facebook/wav2vec2-xls-r-300m, achieving a 65.15% word error rate (WER) on the Common Voice 8 test set.