<!-- 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_lr_en3_0030
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: 1.8884
- Train Accuracy: 0.0206
- Train Wermet: 9.3320
- Train Wermet Syl: 9.0384
- Validation Loss: 2.2312
- Validation Accuracy: 0.0160
- Validation Wermet: 17.0268
- Validation Wermet Syl: 15.2047
- Epoch: 29
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': 0.001, '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 |
|---|---|---|---|---|---|---|---|---|
| 5.0580 | 0.0110 | 1.8635 | 1.7118 | 4.0077 | 0.0112 | 1.0399 | 1.0195 | 0 |
| 4.7330 | 0.0115 | 0.9446 | 0.9262 | 3.9889 | 0.0113 | 0.9757 | 0.9619 | 1 |
| 4.6832 | 0.0116 | 0.8889 | 0.8637 | 3.9832 | 0.0114 | 0.9574 | 0.9276 | 2 |
| 4.6668 | 0.0116 | 0.9362 | 0.9592 | 3.9389 | 0.0113 | 0.9939 | 1.0310 | 3 |
| 4.6252 | 0.0117 | 1.0167 | 1.1679 | 3.9158 | 0.0114 | 0.9633 | 0.9764 | 4 |
| 4.6026 | 0.0117 | 1.0596 | 1.2533 | 3.8896 | 0.0114 | 0.9953 | 1.0541 | 5 |
| 4.5658 | 0.0118 | 1.1222 | 1.3998 | 3.8228 | 0.0116 | 0.9368 | 0.9177 | 6 |
| 4.4715 | 0.0120 | 1.0840 | 1.3327 | 3.7310 | 0.0117 | 0.9284 | 0.9338 | 7 |
| 4.3515 | 0.0122 | 1.5346 | 2.0632 | 3.6182 | 0.0119 | 0.9122 | 0.9112 | 8 |
| 4.1520 | 0.0126 | 1.7418 | 2.3436 | 3.2869 | 0.0124 | 1.3462 | 1.8561 | 9 |
| 3.8516 | 0.0132 | 1.8839 | 2.6071 | 3.0980 | 0.0128 | 0.9534 | 0.9652 | 10 |
| 3.5680 | 0.0139 | 2.4447 | 3.4321 | 2.9746 | 0.0129 | 1.1678 | 1.6347 | 11 |
| 3.3589 | 0.0144 | 2.4698 | 3.4460 | 2.6950 | 0.0137 | 1.0842 | 1.5304 | 12 |
| 3.1696 | 0.0149 | 1.5290 | 2.1570 | 2.5462 | 0.0141 | 0.7527 | 0.8018 | 13 |
| 3.0438 | 0.0154 | 1.1658 | 1.5877 | 2.8403 | 0.0133 | 0.8122 | 0.8351 | 14 |
| 3.5014 | 0.0139 | 1.6667 | 2.1542 | 3.0705 | 0.0127 | 0.9106 | 0.9810 | 15 |
| 3.2493 | 0.0146 | 3.1163 | 4.0054 | 2.6965 | 0.0137 | 0.8412 | 0.9477 | 16 |
| 3.0545 | 0.0153 | 2.3470 | 3.2466 | 2.5400 | 0.0143 | 1.1155 | 1.5200 | 17 |
| 2.8967 | 0.0159 | 3.2617 | 4.3707 | 2.6836 | 0.0138 | 1.4573 | 1.8857 | 18 |
| 2.7463 | 0.0164 | 3.3160 | 4.4960 | 2.3931 | 0.0146 | 1.1235 | 1.4960 | 19 |
| 2.5674 | 0.0172 | 2.8230 | 3.9353 | 2.3981 | 0.0148 | 1.0360 | 1.3746 | 20 |
| 2.4806 | 0.0176 | 1.6197 | 2.2578 | 2.2863 | 0.0152 | 0.7611 | 0.8278 | 21 |
| 2.5360 | 0.0173 | 2.4230 | 3.1274 | 2.3243 | 0.0150 | 1.1862 | 1.6197 | 22 |
| 2.3174 | 0.0184 | 2.6035 | 3.5526 | 2.2607 | 0.0154 | 1.3776 | 2.0276 | 23 |
| 2.2866 | 0.0185 | 2.2680 | 3.1348 | 2.3851 | 0.0151 | 0.9925 | 1.2402 | 24 |
| 2.2986 | 0.0184 | 6.3754 | 7.0512 | 2.3740 | 0.0150 | 4.0136 | 5.1154 | 25 |
| 2.2190 | 0.0188 | 6.7424 | 7.3382 | 2.2337 | 0.0154 | 9.5354 | 9.3299 | 26 |
| 2.0896 | 0.0195 | 7.7193 | 7.9457 | 2.2907 | 0.0156 | 4.0386 | 4.6607 | 27 |
| 1.9741 | 0.0201 | 8.8214 | 8.6453 | 2.2896 | 0.0154 | 15.8802 | 14.4870 | 28 |
| 1.8884 | 0.0206 | 9.3320 | 9.0384 | 2.2312 | 0.0160 | 17.0268 | 15.2047 | 29 |
Framework versions
- Transformers 4.34.0.dev0
- TensorFlow 2.13.0
- Tokenizers 0.13.3
