whisper-tiny-ml

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

• Loss: 0.2092
• Wer: 79.8896

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: 2
• eval_batch_size: 2
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 8
• 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: 5000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
1.4609	1.0316	500	1.1205	132.1684
0.9694	2.0632	1000	0.7589	100.8175
0.4373	4.0264	1500	0.2443	90.7214
0.2336	5.058	2000	0.2078	84.0997
0.1689	7.0212	2500	0.1942	79.9714
0.1322	8.0528	3000	0.1992	79.7466
0.1063	10.016	3500	0.2044	80.4210
0.0892	11.0476	4000	0.2040	78.7247
0.0755	13.0108	4500	0.2106	79.9918
0.0672	14.0424	5000	0.2092	79.8896

Framework versions

• Transformers 4.50.3
• Pytorch 2.6.0+cu124
• Datasets 3.5.0
• Tokenizers 0.21.1