OmarKhattab/whisper-arabic

Arabic Whisper

This model is a fine-tuned version of openai/whisper-small on the Common Voice 13.0 dataset. It achieves the following results on the evaluation set:

• Loss: 0.2682
• Wer: 38.5566

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 1e-05
• train_batch_size: 16
• eval_batch_size: 8
• seed: 42
• optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 500
• training_steps: 4000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.2829	0.4148	1000	0.3279	44.4093
0.1824	0.8295	2000	0.2965	44.4240
0.1039	1.2443	3000	0.2791	39.7591
0.0965	1.6591	4000	0.2682	38.5566

Framework versions

• Transformers 4.51.3
• Pytorch 2.5.1+cu121
• Datasets 3.5.0
• Tokenizers 0.21.1