ubulut/whisper-tiny-quran-lite

Whisper Tiny AR - Quran

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

• Loss: 2.2877
• Wer: 94.3065

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
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• 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
0.0026	17.2414	1000	2.0479	100.2997
0.0004	34.4828	2000	2.1836	94.0925
0.0002	51.7241	3000	2.2654	94.7346
0.0001	68.9655	4000	2.2877	94.3065

Framework versions

• Transformers 4.42.3
• Pytorch 2.3.0+cu121
• Datasets 2.20.0
• Tokenizers 0.19.1