gerryc
/

whisper-medium-ar

Automatic Speech Recognition

Transformers

PyTorch

Generated from Trainer

Eval Results (legacy)

Model card Files Files and versions

xet

Metrics Training metrics Community

Whisper Medium Ar - gerryc

Model was trained on CommonVoice Train. Tensorboard eval is on 256 samples of CommonVoice Dev.

Not normalized or lowercased. Evaluated and saved every 2500 steps. This model was overtrained and is overfitted. About 2000 to 4000 steps is around the best spot to stop training.

Downloads last month: 8

Evaluation results

Wer on FLEURS
test set self-reported

52.800