2026-02-03_18-23-36

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

• Loss: 1.1047
• Wer: 11.3055

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: Use 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: 4000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
2.1664	0.1123	500	1.2593	13.2340
1.1469	0.2247	1000	1.1781	11.9997
1.1	0.3370	1500	1.1463	11.7543
1.0623	0.4493	2000	1.1338	11.6869
1.0446	0.5617	2500	1.1211	11.5059
1.0408	0.6740	3000	1.1142	11.6748
1.0323	0.7863	3500	1.1078	11.4361
1.0203	0.8987	4000	1.1047	11.3055

Framework versions

• Transformers 4.51.3
• Pytorch 2.6.0+cu124
• Datasets 3.6.0
• Tokenizers 0.21.1