raghadOmar/whisper-small-ar

Zolfa-raghadomar

This model is a fine-tuned version of tarteel-ai/whisper-base-ar-quran on the Zolfa Dataset dataset. It achieves the following results on the evaluation set:

• Loss: 0.2374
• Wer: 14.2857

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: 4
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 5
• training_steps: 1000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.0669	0.6993	100	0.2045	21.4286
0.024	1.3986	200	0.2314	17.3469
0.0085	2.0979	300	0.2133	16.3265
0.0085	2.7972	400	0.2120	14.2857
0.0052	3.4965	500	0.2225	14.2857
0.0036	4.1958	600	0.2354	14.2857
0.0016	4.8951	700	0.2322	14.2857
0.0002	5.5944	800	0.2373	14.2857
0.0003	6.2937	900	0.2372	14.2857
0.0012	6.9930	1000	0.2374	14.2857

Framework versions

• Transformers 4.41.2
• Pytorch 2.3.0+cu121
• Datasets 2.19.2
• Tokenizers 0.19.1