whisper-tiny-minds14-en-us
This model is a fine-tuned version of openai/whisper-tiny on the PolyAI/minds14 dataset. It achieves the following results on the evaluation set:
- Loss: 0.4744
- Wer: 0.3241
- Wer Ortho: 0.3362
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: 8
- 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
- num_epochs: 5
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer | Wer Ortho |
|---|---|---|---|---|---|
| 0.3972 | 1.7857 | 100 | 0.4791 | 0.3595 | 0.3732 |
| 0.1725 | 3.5714 | 200 | 0.4744 | 0.3241 | 0.3362 |
| 0.0939 | 5.0 | 280 | 0.4832 | 0.3335 | 0.3473 |
Framework versions
- Transformers 5.22.1
- Pytorch 2.11.0+cu130
- Datasets 5.1.0
- Tokenizers 0.23.3