<!-- 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_char_cv12_pad_lob100_low_sup__0015
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: 1.1549
- Train Accuracy: 0.0728
- Train Wermet: 1.6202
- Validation Loss: 1.0353
- Validation Accuracy: 0.0478
- Validation Wermet: 2.9217
- Epoch: 14
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': 1e-05, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False, 'weight_decay_rate': 0.01}
- training_precision: float32
Training results
| Train Loss | Train Accuracy | Train Wermet | Validation Loss | Validation Accuracy | Validation Wermet | Epoch |
|---|---|---|---|---|---|---|
| 2.5942 | 0.0399 | 3.6402 | 1.9371 | 0.0319 | 16.1531 | 0 |
| 1.8766 | 0.0532 | 6.8384 | 1.7437 | 0.0343 | 15.0408 | 1 |
| 1.7251 | 0.0570 | 5.9150 | 1.6630 | 0.0358 | 10.5002 | 2 |
| 1.6457 | 0.0591 | 5.1153 | 1.5993 | 0.0369 | 10.4737 | 3 |
| 1.5935 | 0.0604 | 4.8231 | 1.5582 | 0.0375 | 8.5794 | 4 |
| 1.5526 | 0.0615 | 4.1987 | 1.5103 | 0.0385 | 9.4130 | 5 |
| 1.5165 | 0.0625 | 4.0179 | 1.4812 | 0.0391 | 6.6025 | 6 |
| 1.4868 | 0.0633 | 3.6770 | 1.4465 | 0.0399 | 6.7562 | 7 |
| 1.4565 | 0.0642 | 3.3851 | 1.4326 | 0.0402 | 6.3327 | 8 |
| 1.4271 | 0.0650 | 3.2883 | 1.3788 | 0.0413 | 6.5933 | 9 |
| 1.3965 | 0.0659 | 3.0822 | 1.3558 | 0.0415 | 5.7852 | 10 |
| 1.3541 | 0.0671 | 2.8659 | 1.2958 | 0.0429 | 5.2978 | 11 |
| 1.3066 | 0.0684 | 2.4942 | 1.2323 | 0.0440 | 4.9600 | 12 |
| 1.2401 | 0.0703 | 2.0745 | 1.1430 | 0.0456 | 3.6837 | 13 |
| 1.1549 | 0.0728 | 1.6202 | 1.0353 | 0.0478 | 2.9217 | 14 |
Framework versions
- Transformers 4.33.0.dev0
- TensorFlow 2.13.0
- Tokenizers 0.13.3
