Model Card for wav2vec2-da-2025-Nov

This model is trained in the Alvenir/rnd-asr-training repository using the follwing command:

CUDA_VISIBLE_DEVICES=0 python src/scripts/finetune_asr_model.py model=wav2vec2-small model_id=wav2vec2-alvenir2025 models_dir=/mnt/data/asr-training/training-runs/coral2 'characters_to_keep="abcdefghijklmnopqrstuvwxyzæøåéü"' save_total_limit=5 experiment_tracking=wandb datasets=[common_voice_23,coral2read,coral2conv,gyldendal,conv_finance] dataset_probabilities=[0.05,0.40,0.10,0.40,0.05]