<!-- 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_syl_noforce__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: 3.4710
- Train Accuracy: 0.0157
- Train Wermet: 0.7681
- Validation Loss: 3.0318
- Validation Accuracy: 0.0138
- Validation Wermet: 0.8455
- 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 |
|---|---|---|---|---|---|---|
| 5.2961 | 0.0113 | 1.9043 | 3.9402 | 0.0116 | 0.9526 | 0 |
| 4.6207 | 0.0121 | 0.8740 | 3.7957 | 0.0120 | 0.9397 | 1 |
| 4.4142 | 0.0128 | 0.8473 | 3.6045 | 0.0124 | 0.8988 | 2 |
| 4.1915 | 0.0135 | 0.8361 | 3.4445 | 0.0128 | 0.9019 | 3 |
| 4.0072 | 0.0140 | 0.8260 | 3.3268 | 0.0131 | 0.8816 | 4 |
| 3.8559 | 0.0145 | 0.8084 | 3.2440 | 0.0133 | 0.8592 | 5 |
| 3.7359 | 0.0149 | 0.7986 | 3.1751 | 0.0135 | 0.8598 | 6 |
| 3.6368 | 0.0152 | 0.7891 | 3.1298 | 0.0136 | 0.8398 | 7 |
| 3.5465 | 0.0154 | 0.7775 | 3.0736 | 0.0138 | 0.8606 | 8 |
| 3.4710 | 0.0157 | 0.7681 | 3.0318 | 0.0138 | 0.8455 | 9 |
Framework versions
- Transformers 4.33.0.dev0
- TensorFlow 2.13.0
- Tokenizers 0.13.3
