whisper-tiny-finetuned-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: 0.6436
- Wer Ortho: 0.2901
- Wer: 0.2692
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: 16
- 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: 500
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer Ortho | Wer |
|---|---|---|---|---|---|
| 0.2901 | 3.5714 | 100 | 0.5412 | 0.2946 | 0.2668 |
| 0.0542 | 7.1429 | 200 | 0.5759 | 0.2826 | 0.2576 |
| 0.007 | 10.7143 | 300 | 0.6241 | 0.2870 | 0.2631 |
| 0.0028 | 14.2857 | 400 | 0.6381 | 0.2870 | 0.2656 |
| 0.0022 | 17.8571 | 500 | 0.6436 | 0.2901 | 0.2692 |
Framework versions
- Transformers 4.57.3
- Pytorch 2.9.0+cu126
- Datasets 4.0.0
- Tokenizers 0.22.1