Whisper Small Indonesian
This model is a fine-tuned version of openai/whisper-base on the mozilla-foundation/common_voice_9_0 id dataset. It achieves the following results on the evaluation set:
- Loss: 0.3793
- Wer: 23.1930
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: 8
- eval_batch_size: 4
- 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: 5000
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.4648 | 0.97 | 1000 | 0.4258 | 27.6236 |
| 0.2992 | 1.94 | 2000 | 0.3831 | 24.4444 |
| 0.1597 | 2.9 | 3000 | 0.3778 | 23.6163 |
| 0.1137 | 3.87 | 4000 | 0.3793 | 23.1930 |
| 0.0632 | 4.84 | 5000 | 0.3893 | 23.5013 |
Framework versions
- Transformers 4.31.0.dev0
- Pytorch 2.0.1+cu117
- Datasets 2.13.1
- Tokenizers 0.13.3