whisper-tiny-minds14
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: 0.6360
- Wer Ortho: 0.3325
- Wer: 0.3300
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: constant_with_warmup
- lr_scheduler_warmup_steps: 50
- training_steps: 500
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer Ortho | Wer |
|---|---|---|---|---|---|
| 0.2676 | 3.5714 | 100 | 0.4847 | 0.3479 | 0.3412 |
| 0.0273 | 7.1429 | 200 | 0.5589 | 0.3424 | 0.3312 |
| 0.0030 | 10.7143 | 300 | 0.6007 | 0.3381 | 0.3318 |
| 0.0009 | 14.2857 | 400 | 0.6201 | 0.3319 | 0.3282 |
| 0.0011 | 17.8571 | 500 | 0.6360 | 0.3325 | 0.3300 |
Framework versions
- Transformers 5.20.2
- Pytorch 2.11.0+cu130
- Datasets 4.8.5
- Tokenizers 0.23.3