Whisper Small Indonesian
This model is a fine-tuned version of openai/whisper-tiny on the mozilla-foundation/common_voice_9_0 id dataset. It achieves the following results on the evaluation set:
- Loss: 0.5086
- Wer: 32.1003
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: 12
- eval_batch_size: 6
- 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 |
|---|---|---|---|---|
| 0.5121 | 1.45 | 1000 | 0.5645 | 36.2595 |
| 0.3401 | 2.9 | 2000 | 0.5052 | 32.9377 |
| 0.1855 | 4.35 | 3000 | 0.5086 | 32.1003 |
| 0.1638 | 5.81 | 4000 | 0.5088 | 32.1831 |
| 0.1047 | 7.26 | 5000 | 0.5143 | 32.1601 |
Framework versions
- Transformers 4.31.0.dev0
- Pytorch 2.0.1+cu117
- Datasets 2.13.1
- Tokenizers 0.13.3