<!-- 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-base-en
This model is a fine-tuned version of on the None dataset. It achieves the following results on the evaluation set:
- Loss: 6.6255
- Wer: 100.2326
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: 64
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 100
- training_steps: 2000
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 9.6216 | 0.1 | 200 | 8.7717 | 96.4409 |
| 8.6624 | 0.2 | 400 | 8.2638 | 100.2048 |
| 8.2176 | 0.3 | 600 | 7.8444 | 100.2639 |
| 7.838 | 0.4 | 800 | 7.5007 | 100.1601 |
| 7.5379 | 1.03 | 1000 | 7.2316 | 100.1941 |
| 7.3023 | 1.13 | 1200 | 7.0273 | 100.1869 |
| 7.1307 | 1.23 | 1400 | 6.8562 | 100.1869 |
| 6.9728 | 1.33 | 1600 | 6.7286 | 100.2272 |
| 6.8891 | 1.43 | 1800 | 6.6533 | 100.2326 |
| 6.8301 | 2.06 | 2000 | 6.6255 | 100.2326 |
Framework versions
- Transformers 4.34.0.dev0
- Pytorch 2.0.0+cu118
- Datasets 2.14.4
- Tokenizers 0.13.3
