train_batch_size=16

eval_batch_size=8

optimizer: Adam

learning_rate=1e-5

warmup_steps=500

max_steps=4000
    
eval_steps=1000


metric_for_best_model="wer"

Training results

Training Loss	Step	Validation Loss	Wer
0.2811	1000	0.393018	53.778349
0.2356	2000	0.348794	47.793591
0.1705	3000	0.332207	45.758883
0.1476	4000	0.322550	44.976586

MMars/whisper-small-ar

Whisper-small-ar - Mourad Mars

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

MMars/
whisper-small-ar