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: 0.3042
- Wer: 12.6662
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
- gradient_accumulation_steps: 2
- total_train_batch_size: 16
- 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 |
|---|---|---|---|---|
| 0.2062 | 1.94 | 1000 | 0.2485 | 14.3639 |
| 0.0373 | 3.87 | 2000 | 0.2622 | 13.4115 |
| 0.0077 | 5.81 | 3000 | 0.3042 | 12.6662 |
| 0.0019 | 7.74 | 4000 | 0.3233 | 12.8042 |
| 0.0013 | 9.68 | 5000 | 0.3306 | 12.9193 |
Framework versions
- Transformers 4.31.0.dev0
- Pytorch 2.0.1+cu117
- Datasets 2.13.1
- Tokenizers 0.13.3