Fine-tuned Whisper Small model achieved 37.5% WER and 7.45% CER on Baniwa language with only 0.54 hours of training speech

The best model achieved a WER of 37.5% and a CER of 7.45%, demonstrating that multilingual foundation models can be successfully adapted to extremely low-resource indigenous languages

http://arxiv.org/abs/2608.26060v1