<!-- This model card has been generated automatically according to the information Keras had access to. You should probably proofread and complete it, then remove this comment. -->
whisper_attention_1_0005
This model is a fine-tuned version of openai/whisper-tiny on an unknown dataset. It achieves the following results on the evaluation set:
- Train Loss: 4.0706
- Train Accuracy: 0.0133
- Train Wermet: 1.1544
- Validation Loss: 3.3059
- Validation Accuracy: 0.0127
- Validation Wermet: 2.5474
- Epoch: 4
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:
- optimizer: {'name': 'AdamWeightDecay', 'learning_rate': 1e-05, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False, 'weight_decay_rate': 0.01}
- training_precision: float32
Training results
| Train Loss | Train Accuracy | Train Wermet | Validation Loss | Validation Accuracy | Validation Wermet | Epoch |
|---|---|---|---|---|---|---|
| 4.3421 | 0.0126 | 1.0868 | 3.5901 | 0.0122 | 1.7563 | 0 |
| 4.2960 | 0.0127 | 1.0419 | 3.5479 | 0.0122 | 1.6770 | 1 |
| 4.2437 | 0.0128 | 1.1301 | 3.4931 | 0.0124 | 1.2281 | 2 |
| 4.1660 | 0.0130 | 1.1307 | 3.4015 | 0.0125 | 1.7745 | 3 |
| 4.0706 | 0.0133 | 1.1544 | 3.3059 | 0.0127 | 2.5474 | 4 |
Framework versions
- Transformers 4.33.0.dev0
- TensorFlow 2.13.0
- Tokenizers 0.13.3
