Whisper Small Indonesian
This model is a fine-tuned version of openai/whisper-small on the mozilla-foundation/common_voice_9_0 id dataset. It achieves the following results on the evaluation set:
- Loss: 0.4077
- Wer: 19.1028
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: 0.0001
- train_batch_size: 4
- eval_batch_size: 2
- 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 |
|---|---|---|---|---|
| 0.9789 | 0.48 | 1000 | 0.8522 | 41.7483 |
| 0.7245 | 0.97 | 2000 | 0.7121 | 36.8162 |
| 0.3335 | 1.45 | 3000 | 0.5499 | 28.7141 |
| 0.2575 | 1.94 | 4000 | 0.4435 | 22.0934 |
| 0.0593 | 2.42 | 5000 | 0.4077 | 19.1028 |
Framework versions
- Transformers 4.31.0.dev0
- Pytorch 2.0.1+cu117
- Datasets 2.13.1
- Tokenizers 0.13.3