<!-- 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. -->
wh_4_sun_syl_w_0_lr_8en5_new_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: 3.7874
- Train Accuracy: 0.0142
- Train Wermet: 0.7029
- Train Wermet Syl: 0.6765
- Validation Loss: 2.3850
- Validation Accuracy: 0.0149
- Validation Wermet: 0.6752
- Validation Wermet Syl: 0.6324
- 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': 8e-05, '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 |
|---|---|---|---|---|---|---|---|---|
| 4.9473 | 0.0111 | 1.1332 | 1.0824 | 3.9300 | 0.0113 | 0.9772 | 0.9710 | 0 |
| 4.6712 | 0.0117 | 0.8506 | 0.8117 | 3.8878 | 0.0115 | 0.9268 | 0.8881 | 1 |
| 4.6221 | 0.0117 | 0.8367 | 0.7959 | 3.8674 | 0.0115 | 0.9247 | 0.8888 | 2 |
| 4.5022 | 0.0121 | 0.7836 | 0.7413 | 3.5242 | 0.0123 | 0.8394 | 0.7987 | 3 |
| 3.7874 | 0.0142 | 0.7029 | 0.6765 | 2.3850 | 0.0149 | 0.6752 | 0.6324 | 4 |
Framework versions
- Transformers 4.34.0.dev0
- TensorFlow 2.13.0
- Tokenizers 0.13.3
