<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
whisper-tiny-testing-data-v2
This model is a fine-tuned version of openai/whisper-tiny on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.2767
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:
- learning_rate: 0.0015
- train_batch_size: 32
- eval_batch_size: 8
- seed: 42
- distributed_type: tpu
- num_devices: 8
- total_train_batch_size: 256
- total_eval_batch_size: 64
- optimizer: Adam with betas=(0.9,0.98) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 1024
- training_steps: 63840
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.0995 | 1.0 | 3192 | 1.3241 |
| 0.7743 | 2.0 | 6384 | 0.9942 |
| 0.6406 | 3.0 | 9576 | 0.8284 |
| 0.5466 | 4.0 | 12768 | 0.7167 |
| 0.4858 | 5.0 | 15960 | 0.6410 |
| 0.4256 | 6.0 | 19152 | 0.5789 |
| 0.3925 | 7.0 | 22344 | 0.5371 |
| 0.3559 | 8.0 | 25536 | 0.4963 |
| 0.332 | 9.0 | 28728 | 0.4686 |
| 0.3041 | 10.0 | 31920 | 0.4385 |
| 0.2823 | 11.0 | 35112 | 0.4139 |
| 0.2634 | 12.0 | 38304 | 0.3888 |
| 0.2387 | 13.0 | 41496 | 0.3695 |
| 0.2289 | 14.0 | 44688 | 0.3524 |
| 0.2109 | 15.0 | 47880 | 0.3336 |
| 0.1971 | 16.0 | 51072 | 0.3188 |
| 0.1863 | 17.0 | 54264 | 0.3045 |
| 0.1703 | 18.0 | 57456 | 0.2919 |
| 0.1598 | 19.0 | 60648 | 0.2828 |
| 0.1528 | 20.0 | 63840 | 0.2767 |
Framework versions
- Transformers 4.29.2
- Pytorch 2.1.0a0+gitcc01568
- Datasets 2.12.0
- Tokenizers 0.13.3
