<!-- 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_5en5_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: 4.3462
- Train Accuracy: 0.0127
- Train Wermet: 0.7425
- Train Wermet Syl: 0.6956
- Validation Loss: 3.2344
- Validation Accuracy: 0.0129
- Validation Wermet: 0.8044
- Validation Wermet Syl: 0.7606
- 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': 5e-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 |
|---|---|---|---|---|---|---|---|---|
| 4.9238 | 0.0114 | 1.0862 | 0.9770 | 3.9338 | 0.0113 | 0.9552 | 0.9254 | 0 |
| 4.6719 | 0.0117 | 0.8528 | 0.8103 | 3.9007 | 0.0115 | 0.9402 | 0.9039 | 1 |
| 4.6187 | 0.0118 | 0.8301 | 0.7838 | 3.8610 | 0.0114 | 0.9577 | 0.9437 | 2 |
| 4.5640 | 0.0120 | 0.7789 | 0.7297 | 3.7621 | 0.0118 | 0.8545 | 0.8033 | 3 |
| 4.3462 | 0.0127 | 0.7425 | 0.6956 | 3.2344 | 0.0129 | 0.8044 | 0.7606 | 4 |
Framework versions
- Transformers 4.34.0.dev0
- TensorFlow 2.13.0
- Tokenizers 0.13.3
