GAL500

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

• Loss: 0.2507
• Wer: 25.2114

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: 5e-05
• train_batch_size: 16
• eval_batch_size: 8
• seed: 42
• optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 500
• training_steps: 5000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.5194	0.3199	1000	0.4919	45.8570
0.4237	0.6398	2000	0.3681	37.4251
0.349	0.9597	3000	0.3047	30.5457
0.2235	1.2796	4000	0.2758	27.5404
0.188	1.5995	5000	0.2507	25.2114

Framework versions

• Transformers 4.54.1
• Pytorch 2.6.0+cu124
• Datasets 4.0.0
• Tokenizers 0.21.1