<!-- 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_8en5_0010
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: 0.8174
- Train Accuracy: 0.0283
- Train Wermet: 0.1811
- Train Wermet Syl: 0.1904
- Validation Loss: 0.9411
- Validation Accuracy: 0.0211
- Validation Wermet: 0.2923
- Validation Wermet Syl: 0.2616
- Epoch: 9
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 |
|---|---|---|---|---|---|---|---|---|
| 4.9173 | 0.0113 | 1.2294 | 1.1313 | 4.0041 | 0.0114 | 0.9465 | 0.9188 | 0 |
| 4.6657 | 0.0117 | 0.8575 | 0.8170 | 3.8938 | 0.0114 | 0.9522 | 0.9285 | 1 |
| 4.6204 | 0.0118 | 0.8349 | 0.7915 | 3.8636 | 0.0115 | 0.9356 | 0.9050 | 2 |
| 4.5401 | 0.0120 | 0.7910 | 0.7460 | 3.7044 | 0.0119 | 0.8709 | 0.8276 | 3 |
| 4.0455 | 0.0134 | 0.7289 | 0.6945 | 2.6218 | 0.0143 | 0.7096 | 0.6705 | 4 |
| 2.8030 | 0.0175 | 0.5780 | 0.5793 | 1.9960 | 0.0162 | 0.5301 | 0.5039 | 5 |
| 1.9136 | 0.0214 | 0.4292 | 0.4643 | 1.3747 | 0.0187 | 0.4114 | 0.3873 | 6 |
| 1.3530 | 0.0245 | 0.3169 | 0.3444 | 1.0619 | 0.0205 | 0.3371 | 0.3019 | 7 |
| 1.0724 | 0.0263 | 0.2442 | 0.2674 | 0.9876 | 0.0209 | 0.3075 | 0.2717 | 8 |
| 0.8174 | 0.0283 | 0.1811 | 0.1904 | 0.9411 | 0.0211 | 0.2923 | 0.2616 | 9 |
Framework versions
- Transformers 4.34.0.dev0
- TensorFlow 2.13.0
- Tokenizers 0.13.3
