<!-- 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-small-ko-normalized-debug
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: 0.6194
- Wer: 0.3928
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: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 100
- num_epochs: 3
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| No log | 1.0 | 4 | 0.6447 | 0.4031 |
| No log | 2.0 | 8 | 0.6389 | 0.3992 |
| 0.4891 | 3.0 | 12 | 0.6194 | 0.3928 |
Framework versions
- Transformers 4.28.0.dev0
- Pytorch 1.13.1+cu117
- Datasets 2.11.0
- Tokenizers 0.13.2
