<!-- 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_4_with_init_sun_syl_wd_0__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: 4.6282
- Train Accuracy: 0.0118
- Train Wermet: 0.8286
- Train Wermet Syl: 0.7805
- Validation Loss: 3.8738
- Validation Accuracy: 0.0114
- Validation Wermet: 0.9433
- Validation Wermet Syl: 0.9119
- 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}
- training_precision: float32
Training results
| Train Loss | Train Accuracy | Train Wermet | Train Wermet Syl | Validation Loss | Validation Accuracy | Validation Wermet | Validation Wermet Syl | Epoch |
|---|---|---|---|---|---|---|---|---|
| 5.3409 | 0.0111 | 1.3547 | 1.2898 | 3.9789 | 0.0114 | 0.9710 | 0.9563 | 0 |
| 4.7143 | 0.0116 | 0.8622 | 0.8228 | 3.9404 | 0.0113 | 0.9823 | 0.9735 | 1 |
| 4.6752 | 0.0117 | 0.8472 | 0.8057 | 3.9081 | 0.0114 | 0.9579 | 0.9359 | 2 |
| 4.6500 | 0.0117 | 0.8382 | 0.7945 | 3.8820 | 0.0115 | 0.9213 | 0.8856 | 3 |
| 4.6282 | 0.0118 | 0.8286 | 0.7805 | 3.8738 | 0.0114 | 0.9433 | 0.9119 | 4 |
Framework versions
- Transformers 4.34.0.dev0
- TensorFlow 2.13.0
- Tokenizers 0.13.3
