whisper-base.en-disflunecy-version6

This model is a fine-tuned version of openai/whisper-base.en on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.3070
• Wer: 13.0532

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: 8
• eval_batch_size: 4
• 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: 50
• num_epochs: 7

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
1.0113	1.0	113	0.5012	12.2006
0.264	2.0	226	0.2433	11.0637
0.117	3.0	339	0.2396	11.3276
0.076	4.0	452	0.2522	11.8961
0.0496	5.0	565	0.2726	12.8096
0.0331	6.0	678	0.2930	12.6675
0.0231	7.0	791	0.3070	13.0532

Framework versions

• Transformers 4.51.3
• Pytorch 2.6.0+cu124
• Datasets 3.5.0
• Tokenizers 0.21.1