whisper-small

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: 0.7639
• Wer: 0.2875

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: 32
• eval_batch_size: 32
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 64
• optimizer: Use adafactor and the args are: No additional optimizer arguments
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 100
• training_steps: 1000

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.0001	62.5333	500	0.7211	0.2680
0.0	125.0	1000	0.7639	0.2875

Framework versions

• Transformers 4.51.0
• Pytorch 2.8.0+cu129
• Datasets 3.6.0
• Tokenizers 0.21.4