whisper-tiny-finetuned-minds14
This model is a fine-tuned version of openai/whisper-tiny on the Minds14 dataset. It achieves the following results on the evaluation set:
- Loss: 0.6368
- Wer Ortho: 0.3540
- Wer: 0.3522
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 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: 1000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer Ortho | Wer |
|---|---|---|---|---|---|
| 0.7132 | 7.1429 | 200 | 0.4647 | 0.3554 | 0.3477 |
| 0.0044 | 14.2857 | 400 | 0.5662 | 0.3520 | 0.3471 |
| 0.0006 | 21.4286 | 600 | 0.5970 | 0.3540 | 0.3509 |
| 0.0004 | 28.5714 | 800 | 0.6191 | 0.3547 | 0.3515 |
| 0.0002 | 35.7143 | 1000 | 0.6368 | 0.3540 | 0.3522 |
Framework versions
- Transformers 4.52.4
- Pytorch 2.6.0+cu124
- Datasets 2.14.4
- Tokenizers 0.21.1