<!-- 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_input_decoder_shift_r_labels_with_force__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: 3.6763
- Train Accuracy: 0.0136
- Train Wermet: 0.7543
- Validation Loss: 3.3183
- Validation Accuracy: 0.0116
- Validation Wermet: 0.8678
- 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': 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 |
|---|---|---|---|---|---|---|
| 5.6249 | 0.0091 | 1.7162 | 4.2965 | 0.0094 | 0.9447 | 0 |
| 4.9223 | 0.0099 | 0.9041 | 4.1562 | 0.0097 | 0.9327 | 1 |
| 4.6814 | 0.0107 | 0.8376 | 3.9245 | 0.0103 | 0.8927 | 2 |
| 4.4407 | 0.0114 | 0.8311 | 3.7252 | 0.0107 | 0.8775 | 3 |
| 4.2445 | 0.0119 | 0.8228 | 3.6283 | 0.0108 | 0.8695 | 4 |
| 4.0889 | 0.0123 | 0.8067 | 3.5310 | 0.0110 | 0.8916 | 5 |
| 3.9575 | 0.0127 | 0.7908 | 3.4478 | 0.0113 | 0.8407 | 6 |
| 3.8547 | 0.0130 | 0.7781 | 3.4227 | 0.0113 | 0.8670 | 7 |
| 3.7599 | 0.0133 | 0.7654 | 3.3519 | 0.0115 | 0.8375 | 8 |
| 3.6763 | 0.0136 | 0.7543 | 3.3183 | 0.0116 | 0.8678 | 9 |
Framework versions
- Transformers 4.34.0.dev0
- TensorFlow 2.13.0
- Tokenizers 0.13.3
