whisper-small-ar

This model is a fine-tuned version of openai/whisper-small on the None dataset. It achieves the following results on the evaluation set:

• Loss: 3.8097
• Wer: 1097.8814

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: 50
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
No log	0.3226	10	4.4535	1724.5763
No log	0.6452	20	4.4159	1724.5763
4.5063	0.9677	30	4.2685	1724.5763
4.5063	1.2903	40	4.0350	1665.6780
4.154	1.6129	50	3.8097	1097.8814

Framework versions

• Transformers 4.40.2
• Pytorch 2.3.0+cu118
• Datasets 2.19.1
• Tokenizers 0.19.1