Hatimdz/whisper-small-ar

whisper small ar

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

• Loss: 0.5258
• Wer: 150.6173

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: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 500
• training_steps: 4000

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.8749	0.32	1000	0.5855	150.4274
0.6537	0.65	2000	0.5461	130.5793
0.7103	0.97	3000	0.5241	278.2526
0.6544	1.29	4000	0.5258	150.6173

Framework versions

• Transformers 4.32.0.dev0
• Pytorch 2.0.1+cu118
• Datasets 2.14.3
• Tokenizers 0.13.3