whisper-tiny-au-en
This model is a fine-tuned version of openai/whisper-tiny on the Common Voice v24 English - en-AU subset for Everything Open 2026 dataset. It achieves the following results on the evaluation set:
- Loss: 0.9041
- Wer: 19.8430
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: 1
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED 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
- training_steps: 20
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 1.0139 | 0.02 | 5 | 1.0289 | 20.9041 |
| 1.0164 | 0.04 | 10 | 1.0065 | 20.6070 |
| 0.9576 | 0.06 | 15 | 0.9599 | 20.4796 |
| 0.8993 | 0.08 | 20 | 0.9041 | 19.8430 |
Framework versions
- Transformers 5.0.0
- Pytorch 2.10.0+cu128
- Datasets 4.0.0
- Tokenizers 0.22.2
- Downloads last month
- 10
Model tree for sotirios-slv/whisper-tiny-au-en
Base model
openai/whisper-tiny