metadata
license: apache-2.0
base_model: openai/whisper-tiny
tags:
- generated_from_keras_callback
model-index:
- name: train_from_raw_cv12_true__0005
results: []
train_from_raw_cv12_true__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: 1.4910
- Train Accuracy: 0.0631
- Train Wermet: 2.8298
- Validation Loss: 1.4213
- Validation Accuracy: 0.0402
- Validation Wermet: 8.9930
- 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': 2e-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 |
|---|---|---|---|---|---|---|
| 2.3396 | 0.0444 | 2.7124 | 1.8124 | 0.0331 | 9.4418 | 0 |
| 1.7496 | 0.0562 | 3.2708 | 1.6529 | 0.0359 | 9.7805 | 1 |
| 1.6254 | 0.0594 | 3.1714 | 1.5874 | 0.0371 | 10.4139 | 2 |
| 1.5490 | 0.0615 | 3.0208 | 1.5102 | 0.0382 | 8.2054 | 3 |
| 1.4910 | 0.0631 | 2.8298 | 1.4213 | 0.0402 | 8.9930 | 4 |
Framework versions
- Transformers 4.33.0.dev0
- TensorFlow 2.13.0
- Tokenizers 0.13.3