<!-- 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_charsplit_new_round4__0045
This model is a fine-tuned version of bigmorning/whisper_charsplit_new_round2__0061 on an unknown dataset. It achieves the following results on the evaluation set:
- Train Loss: 0.0001
- Train Accuracy: 0.0795
- Train Wermet: 9.4087
- Validation Loss: 0.5741
- Validation Accuracy: 0.0774
- Validation Wermet: 8.2489
- Epoch: 44
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 |
|---|---|---|---|---|---|---|
| 0.0009 | 0.0795 | 7.9702 | 0.5713 | 0.0770 | 6.9300 | 0 |
| 0.0011 | 0.0795 | 7.7485 | 0.5743 | 0.0771 | 6.6465 | 1 |
| 0.0011 | 0.0795 | 8.1600 | 0.5748 | 0.0771 | 7.1363 | 2 |
| 0.0008 | 0.0795 | 8.1954 | 0.5845 | 0.0770 | 7.1869 | 3 |
| 0.0009 | 0.0795 | 8.4533 | 0.5771 | 0.0771 | 7.4112 | 4 |
| 0.0009 | 0.0795 | 8.3048 | 0.5912 | 0.0770 | 6.5276 | 5 |
| 0.0008 | 0.0795 | 8.2183 | 0.5810 | 0.0771 | 7.1210 | 6 |
| 0.0011 | 0.0795 | 8.3785 | 0.5861 | 0.0770 | 7.6613 | 7 |
| 0.0010 | 0.0795 | 8.0860 | 0.5811 | 0.0771 | 7.0809 | 8 |
| 0.0009 | 0.0795 | 8.2523 | 0.5894 | 0.0770 | 7.1269 | 9 |
| 0.0006 | 0.0795 | 8.7530 | 0.5819 | 0.0771 | 7.3657 | 10 |
| 0.0007 | 0.0795 | 8.5391 | 0.5773 | 0.0771 | 7.7370 | 11 |
| 0.0010 | 0.0795 | 8.8222 | 0.5894 | 0.0770 | 7.9252 | 12 |
| 0.0014 | 0.0795 | 8.9039 | 0.5880 | 0.0771 | 7.6404 | 13 |
| 0.0009 | 0.0795 | 8.6866 | 0.5777 | 0.0771 | 7.5804 | 14 |
| 0.0006 | 0.0795 | 9.0833 | 0.5736 | 0.0772 | 8.3242 | 15 |
| 0.0003 | 0.0795 | 9.3697 | 0.5732 | 0.0772 | 8.4795 | 16 |
| 0.0006 | 0.0795 | 9.4161 | 0.5838 | 0.0771 | 8.5173 | 17 |
| 0.0011 | 0.0795 | 9.7801 | 0.5967 | 0.0769 | 8.5462 | 18 |
| 0.0016 | 0.0795 | 9.9252 | 0.5824 | 0.0771 | 8.8226 | 19 |
| 0.0009 | 0.0795 | 10.1258 | 0.5813 | 0.0771 | 8.6993 | 20 |
| 0.0006 | 0.0795 | 9.8897 | 0.5784 | 0.0772 | 8.1699 | 21 |
| 0.0009 | 0.0795 | 9.3199 | 0.5971 | 0.0771 | 7.6986 | 22 |
| 0.0018 | 0.0795 | 10.2724 | 0.5924 | 0.0769 | 8.9443 | 23 |
| 0.0012 | 0.0795 | 9.5275 | 0.5783 | 0.0771 | 7.7057 | 24 |
| 0.0010 | 0.0795 | 8.6555 | 0.5738 | 0.0772 | 7.1508 | 25 |
| 0.0005 | 0.0795 | 8.8172 | 0.5775 | 0.0772 | 6.9496 | 26 |
| 0.0005 | 0.0795 | 8.4569 | 0.5860 | 0.0771 | 7.5262 | 27 |
| 0.0012 | 0.0795 | 9.6634 | 0.5917 | 0.0770 | 8.3290 | 28 |
| 0.0011 | 0.0795 | 8.9484 | 0.5855 | 0.0771 | 7.6950 | 29 |
| 0.0007 | 0.0795 | 8.7377 | 0.5882 | 0.0771 | 7.4076 | 30 |
| 0.0005 | 0.0795 | 8.5209 | 0.5855 | 0.0772 | 6.7134 | 31 |
| 0.0009 | 0.0795 | 8.5136 | 0.5862 | 0.0771 | 8.0204 | 32 |
| 0.0011 | 0.0795 | 7.8920 | 0.5788 | 0.0772 | 7.3091 | 33 |
| 0.0008 | 0.0795 | 8.8453 | 0.5776 | 0.0772 | 7.0827 | 34 |
| 0.0007 | 0.0795 | 8.1489 | 0.5822 | 0.0771 | 7.5322 | 35 |
| 0.0008 | 0.0795 | 8.4097 | 0.5864 | 0.0771 | 7.7738 | 36 |
| 0.0012 | 0.0795 | 8.9267 | 0.5956 | 0.0770 | 8.1001 | 37 |
| 0.0012 | 0.0795 | 9.4676 | 0.5829 | 0.0771 | 8.7507 | 38 |
| 0.0009 | 0.0795 | 9.6944 | 0.5773 | 0.0772 | 7.7827 | 39 |
| 0.0004 | 0.0795 | 9.3722 | 0.5718 | 0.0773 | 7.8053 | 40 |
| 0.0002 | 0.0795 | 9.2630 | 0.5717 | 0.0773 | 7.8323 | 41 |
| 0.0001 | 0.0795 | 9.2770 | 0.5734 | 0.0773 | 8.3556 | 42 |
| 0.0000 | 0.0795 | 9.2889 | 0.5743 | 0.0774 | 7.8894 | 43 |
| 0.0001 | 0.0795 | 9.4087 | 0.5741 | 0.0774 | 8.2489 | 44 |
Framework versions
- Transformers 4.32.0.dev0
- TensorFlow 2.12.0
- Tokenizers 0.13.3
