whisper-base-arabic-base-v1.2

This model is a fine-tuned version of openai/whisper-base on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.5987
• Wer: 0.6638

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: 32
• eval_batch_size: 32
• 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_ratio: 0.01
• num_epochs: 3
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.705	1.0	1476	0.6682	0.7129
0.6333	2.0	2952	0.6095	0.5865
0.5086	3.0	4428	0.5987	0.6638

Framework versions

• Transformers 4.53.3
• Pytorch 2.6.0+cu124
• Datasets 3.6.0
• Tokenizers 0.21.2