2026-01-16_17-36-39

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: 0.2727
• Wer: 11.0000

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
1.0815	0.1123	500	0.3266	12.6922
0.2694	0.2247	1000	0.3007	12.1771
0.257	0.3370	1500	0.2890	12.3271
0.2518	0.4493	2000	0.2865	11.4719
0.2367	0.5617	2500	0.2792	11.2891
0.239	0.6740	3000	0.2777	11.5284
0.2262	0.7863	3500	0.2757	10.8821
0.2379	0.8987	4000	0.2727	11.0000

Framework versions

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