<!-- 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_4_with_init_sun_syl_wd_0_lr_en2_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: 4.9546
- Train Accuracy: 0.0111
- Train Wermet: 4.8506
- Train Wermet Syl: 3.7351
- Validation Loss: 4.3022
- Validation Accuracy: 0.0112
- Validation Wermet: 0.9870
- Validation Wermet Syl: 0.9854
- 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': 0.01, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False, 'weight_decay_rate': 0}
- training_precision: float32
Training results
| Train Loss | Train Accuracy | Train Wermet | Train Wermet Syl | Validation Loss | Validation Accuracy | Validation Wermet | Validation Wermet Syl | Epoch |
|---|---|---|---|---|---|---|---|---|
| 39.6121 | 0.0057 | 33.2649 | 25.5768 | 4.5339 | 0.0113 | 0.9851 | 0.9843 | 0 |
| 5.3698 | 0.0107 | 12.0116 | 9.0545 | 4.3408 | 0.0112 | 0.9919 | 0.9915 | 1 |
| 5.1979 | 0.0109 | 9.4008 | 7.1909 | 4.2108 | 0.0113 | 0.9851 | 0.9843 | 2 |
| 5.0669 | 0.0110 | 7.0382 | 5.3339 | 4.1662 | 0.0113 | 0.9851 | 0.9843 | 3 |
| 4.9546 | 0.0111 | 4.8506 | 3.7351 | 4.3022 | 0.0112 | 0.9870 | 0.9854 | 4 |
Framework versions
- Transformers 4.34.0.dev0
- TensorFlow 2.13.0
- Tokenizers 0.13.3
