<!-- 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_wermet_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: 1.8954
- Train Accuracy: 0.0240
- Train Wermet: 16.2471
- Validation Loss: 1.4889
- Validation Accuracy: 0.0266
- Validation Wermet: 14.2782
- 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 |
|---|---|---|---|---|---|---|
| 5.0795 | 0.0116 | 43.8776 | 4.4395 | 0.0122 | 35.4119 | 0 |
| 4.3059 | 0.0131 | 29.7976 | 4.0311 | 0.0143 | 26.0070 | 1 |
| 3.8871 | 0.0148 | 19.3999 | 3.6500 | 0.0158 | 19.2186 | 2 |
| 3.0943 | 0.0184 | 18.3704 | 2.3327 | 0.0226 | 22.5034 | 3 |
| 1.8954 | 0.0240 | 16.2471 | 1.4889 | 0.0266 | 14.2782 | 4 |
Framework versions
- Transformers 4.25.0.dev0
- TensorFlow 2.9.2
- Datasets 2.6.1
- Tokenizers 0.13.2
