<!-- 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__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: 1.5935
- Train Accuracy: 0.0604
- Train Wermet: 4.8231
- Validation Loss: 1.5582
- Validation Accuracy: 0.0375
- Validation Wermet: 8.5794
- 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': 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 |
Framework versions
- Transformers 4.33.0.dev0
- TensorFlow 2.13.0
- Tokenizers 0.13.3
