Whisper Small Ko - Eveready
This model is a fine-tuned version of openai/whisper-small on the Common Voice 13 dataset. It achieves the following results on the evaluation set:
- Loss: 0.6726
- Wer Ortho: 40.0806
- Wer: 38.9728
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: 500
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer Ortho | Wer |
|---|---|---|---|---|---|
| 0.0 | 26.32 | 500 | 0.6726 | 40.0806 | 38.9728 |
Framework versions
- Transformers 4.39.3
- Pytorch 2.2.2+cu121
- Datasets 2.17.1
- Tokenizers 0.15.2
- Downloads last month
- 5
Model tree for Eveready/whisper-small-ko
Base model
openai/whisper-smallDataset used to train Eveready/whisper-small-ko
Evaluation results
- Wer on Common Voice 13test set self-reported38.973