# Parliamentary speech transcription

A fine-tuned version of OpenAI Whisper Large V3 Turbo model, specifically optimized for Swiss German dialects via QLoRa, achieving state-of-the-art performance in Swiss German automatic speech recognition tasks.

A Croatian automatic speech recognition model fine-tuned from facebook/wav2vec2-xls-r-300m, trained on the ParlaSpeech-HR v1.0 dataset

A 300M-parameter speech recognition model fine-tuned on the VoxRex feature extractor, optimized for Nynorsk (New Norwegian), achieving a WER of 12.22% on the NPSC test set

Norwegian automatic speech recognition model fine-tuned from VoxRex, achieving 7.03% word error rate on NPSC dataset