<!-- 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. -->
CodeFairModel
This model is a fine-tuned version of openai/whisper-small on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.1159
- Wer: 301.8049
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-06
- train_batch_size: 16
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 1000
- training_steps: 4000
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.5639 | 0.17 | 500 | 0.5630 | 216.4480 |
| 0.3466 | 0.34 | 1000 | 0.3021 | 161.5513 |
| 0.1646 | 0.52 | 1500 | 0.1757 | 180.8131 |
| 0.1487 | 0.69 | 2000 | 0.1489 | 261.9200 |
| 0.1404 | 0.86 | 2500 | 0.1330 | 280.7831 |
| 0.1262 | 1.03 | 3000 | 0.1230 | 296.8924 |
| 0.1083 | 1.21 | 3500 | 0.1177 | 307.1747 |
| 0.1087 | 1.38 | 4000 | 0.1159 | 301.8049 |
Framework versions
- Transformers 4.32.0.dev0
- Pytorch 2.0.1+cu118
- Datasets 2.14.0
- Tokenizers 0.13.3
