<!-- 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. -->
WhisperFineTuneKoTest
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: 0.5538
- Wer: 77.1400
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: 8
- 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: 4000
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.0002 | 83.33 | 1000 | 0.4433 | 93.2528 |
| 0.0001 | 166.67 | 2000 | 0.5067 | 67.9758 |
| 0.0 | 250.0 | 3000 | 0.5384 | 69.4864 |
| 0.0 | 333.33 | 4000 | 0.5538 | 77.1400 |
Framework versions
- Transformers 4.31.0.dev0
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3
