<!-- 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_0010
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: 3.3187
- Train Accuracy: 0.0155
- Train Wermet: 1.3311
- Validation Loss: 2.6049
- Validation Accuracy: 0.0145
- Validation Wermet: 0.9936
- Epoch: 9
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 |
3.9548 | 0.0136 | 1.1634 | 3.1794 | 0.0131 | 1.3329 | 5 |
3.8140 | 0.0140 | 1.1720 | 3.0775 | 0.0132 | 3.0790 | 6 |
3.6493 | 0.0145 | 1.1813 | 2.8709 | 0.0138 | 1.8756 | 7 |
3.4771 | 0.0151 | 1.2548 | 2.7141 | 0.0142 | 1.6652 | 8 |
3.3187 | 0.0155 | 1.3311 | 2.6049 | 0.0145 | 0.9936 | 9 |
Framework versions
- Transformers 4.33.0.dev0
- TensorFlow 2.13.0
- Tokenizers 0.13.3