aymanebiri/whisper-small-darija

Whisper Small Darija

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

• Loss: 0.6569
• Wer: 46.8729

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 adamw_torch_fused 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: 5000

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.4177	1.7241	1000	0.4935	50.0779
0.1437	3.4483	2000	0.4961	47.4071
0.0349	5.1724	3000	0.5515	49.6105
0.0083	6.8966	4000	0.6211	47.4293
0.0027	8.6207	5000	0.6569	46.8729

Framework versions

• Transformers 5.5.4
• Pytorch 2.11.0+cu130
• Datasets 4.8.4
• Tokenizers 0.22.2