metadata
license: apache-2.0
base_model: openai/whisper-tiny
tags:
- generated_from_keras_callback
model-index:
- name: train_from_raw_cv12_true_suppress__0005
results: []
train_from_raw_cv12_true_suppress__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: 1.4953
- Train Accuracy: 0.0631
- Train Wermet: 1.8208
- Validation Loss: 1.4549
- Validation Accuracy: 0.0397
- Validation Wermet: 4.4667
- 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 |
|---|---|---|---|---|---|---|
| 2.3569 | 0.0439 | 2.6429 | 1.7869 | 0.0339 | 10.1374 | 0 |
| 1.7502 | 0.0561 | 3.2762 | 1.6607 | 0.0360 | 9.6159 | 1 |
| 1.6268 | 0.0595 | 3.0493 | 1.5698 | 0.0374 | 8.6767 | 2 |
| 1.5533 | 0.0614 | 2.3917 | 1.4965 | 0.0387 | 7.2278 | 3 |
| 1.4953 | 0.0631 | 1.8208 | 1.4549 | 0.0397 | 4.4667 | 4 |
Framework versions
- Transformers 4.33.0.dev0
- TensorFlow 2.13.0
- Tokenizers 0.13.3