<!-- 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_new_split_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: 1.3529
- Train Accuracy: 0.0258
- Train Wermet: 17.4367
- Validation Loss: 1.1712
- Validation Accuracy: 0.0276
- Validation Wermet: 17.7695
- 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 |
---|---|---|---|---|---|---|
5.1027 | 0.0113 | 52.5530 | 4.4267 | 0.0121 | 41.4796 | 0 |
4.3285 | 0.0126 | 38.6893 | 3.9835 | 0.0145 | 33.6050 | 1 |
3.4573 | 0.0168 | 30.7714 | 2.5568 | 0.0215 | 31.7559 | 2 |
2.0878 | 0.0226 | 20.5131 | 1.5738 | 0.0257 | 21.2159 | 3 |
1.3529 | 0.0258 | 17.4367 | 1.1712 | 0.0276 | 17.7695 | 4 |
Framework versions
- Transformers 4.27.0.dev0
- TensorFlow 2.11.0
- Tokenizers 0.13.2