<!-- 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_7en5_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: 4.0826
- Train Accuracy: 0.0133
- Train Wermet: 0.7361
- Train Wermet Syl: 0.6973
- Validation Loss: 2.7406
- Validation Accuracy: 0.0139
- Validation Wermet: 0.7479
- Validation Wermet Syl: 0.7097
- 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': 7e-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 |
|---|---|---|---|---|---|---|---|---|
| 4.9248 | 0.0113 | 1.1777 | 1.1068 | 3.9252 | 0.0115 | 0.9215 | 0.8812 | 0 |
| 4.6658 | 0.0117 | 0.8497 | 0.8066 | 3.9186 | 0.0113 | 0.9766 | 0.9699 | 1 |
| 4.6144 | 0.0118 | 0.8224 | 0.7735 | 3.8791 | 0.0115 | 0.9336 | 0.9042 | 2 |
| 4.5388 | 0.0120 | 0.7917 | 0.7466 | 3.6581 | 0.0120 | 0.8508 | 0.8073 | 3 |
| 4.0826 | 0.0133 | 0.7361 | 0.6973 | 2.7406 | 0.0139 | 0.7479 | 0.7097 | 4 |
Framework versions
- Transformers 4.34.0.dev0
- TensorFlow 2.13.0
- Tokenizers 0.13.3
