Whisper Small Ko
This model is a fine-tuned version of openai/whisper-small on the Common Voice 12.0 dataset. It achieves the following results on the evaluation set:
- Loss: 0.4714
- Cer: 100.0
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: 32
- 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: 500
- training_steps: 10000
Training results
| Training Loss | Epoch | Step | Validation Loss | Cer |
|---|---|---|---|---|
| 0.0 | 250.0 | 1000 | 0.2991 | 100.0 |
| 0.0 | 500.0 | 2000 | 0.3324 | 100.0 |
| 0.0 | 750.0 | 3000 | 0.3531 | 100.0 |
| 0.0 | 1000.0 | 4000 | 0.3698 | 100.0 |
| 0.0 | 1250.0 | 5000 | 0.3863 | 100.0 |
| 0.0 | 1500.0 | 6000 | 0.4060 | 100.0 |
| 0.0 | 1750.0 | 7000 | 0.4274 | 100.0 |
| 0.0 | 2000.0 | 8000 | 0.4482 | 100.0 |
| 0.0 | 2250.0 | 9000 | 0.4642 | 100.0 |
| 0.0 | 2500.0 | 10000 | 0.4714 | 100.0 |
Framework versions
- Transformers 4.29.0.dev0
- Pytorch 2.0.0
- Datasets 2.11.0
- Tokenizers 0.11.0
- Downloads last month
- 0