whisper-fine-tuned

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

• Loss: 5.1515
• Wer: 1.0004

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: 0.0001
• train_batch_size: 1
• 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: 5000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
2.1863	1.6393	500	3.5257	0.9991
1.4263	3.2787	1000	4.2011	1.0383
1.1951	4.9180	1500	4.1093	0.9934
0.8698	6.5574	2000	4.3517	1.7507
0.7181	8.1967	2500	4.5794	1.2076
0.718	9.8361	3000	4.6911	1.2960
0.5776	11.4754	3500	4.8927	1.0814
0.624	13.1148	4000	4.9520	1.1319
0.5781	14.7541	4500	5.0590	0.9934
0.5189	16.3934	5000	5.1515	1.0004

Framework versions

• Transformers 4.47.1
• Pytorch 2.5.1+cu121
• Datasets 3.2.0
• Tokenizers 0.21.0