<!-- 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_syl_noforce_nostart__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: 4.2497
- Train Accuracy: 0.0119
- Train Wermet: 0.8211
- Validation Loss: 3.6019
- Validation Accuracy: 0.0110
- Validation Wermet: 0.8640
- 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 |
---|---|---|---|---|---|---|
5.6298 | 0.0091 | 1.6176 | 4.3084 | 0.0092 | 1.0203 | 0 |
4.9271 | 0.0098 | 0.8937 | 4.1324 | 0.0099 | 0.9075 | 1 |
4.6878 | 0.0106 | 0.8360 | 3.9151 | 0.0102 | 0.9003 | 2 |
4.4454 | 0.0113 | 0.8275 | 3.7558 | 0.0106 | 0.8730 | 3 |
4.2497 | 0.0119 | 0.8211 | 3.6019 | 0.0110 | 0.8640 | 4 |
Framework versions
- Transformers 4.33.0.dev0
- TensorFlow 2.13.0
- Tokenizers 0.13.3