<!-- 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-ln-ojpl-2
This model is a fine-tuned version of openai/whisper-tiny on the BrainTheos/ojpl dataset. It achieves the following results on the evaluation set:
- Loss: 1.2661
- Wer Ortho: 50.1855
- Wer: 0.4352
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: 1e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: constant_with_warmup
- lr_scheduler_warmup_steps: 50
- training_steps: 2000
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer Ortho | Wer |
|---|---|---|---|---|---|
| 0.1767 | 11.36 | 500 | 0.9122 | 52.1142 | 0.4579 |
| 0.0191 | 22.73 | 1000 | 1.0786 | 53.7463 | 0.4538 |
| 0.0059 | 34.09 | 1500 | 1.1891 | 53.2641 | 0.4766 |
| 0.0019 | 45.45 | 2000 | 1.2661 | 50.1855 | 0.4352 |
Framework versions
- Transformers 4.31.0.dev0
- Pytorch 2.0.0+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3
