Quran_Whisper_tiny

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

• Loss: 0.0207
• Wer: 229.5347
• Cer: 117.8601

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: 16
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 64
• optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: cosine
• lr_scheduler_warmup_steps: 500
• num_epochs: 1
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer	Cer
0.0495	0.1542	400	0.0480	368.5144	171.2066
0.0286	0.3083	800	0.0298	285.7357	139.7411
0.0216	0.4625	1200	0.0246	228.4060	111.7943
0.0186	0.6166	1600	0.0222	226.2672	114.4094
0.0175	0.7708	2000	0.0211	248.6376	128.6927
0.0173	0.9249	2400	0.0207	229.5347	117.8601

Framework versions

• Transformers 4.47.0
• Pytorch 2.5.1+cu121
• Datasets 3.2.0
• Tokenizers 0.21.0