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: 0.4567
- Wer: 17.5937
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: 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 |
|---|---|---|---|---|
| 0.3743 | 1.45 | 1000 | 0.5498 | 28.2724 |
| 0.1633 | 2.9 | 2000 | 0.5010 | 25.1530 |
| 0.0505 | 4.35 | 3000 | 0.5049 | 22.1670 |
| 0.0136 | 5.81 | 4000 | 0.4631 | 18.6335 |
| 0.0005 | 7.26 | 5000 | 0.4567 | 17.5937 |
Framework versions
- Transformers 4.31.0.dev0
- Pytorch 2.0.1+cu117
- Datasets 2.13.1
- Tokenizers 0.13.3
- Downloads last month
- 2
Inference Providers
NEW
This model is not currently available via any of the supported third-party Inference Providers, and
the model is not deployed on the HF Inference API.
Model tree for TheRains/cv9-special-batch12-lr4-small
Base model
openai/whisper-smallDataset used to train TheRains/cv9-special-batch12-lr4-small
Evaluation results
- Wer on mozilla-foundation/common_voice_9_0 idtest set self-reported17.594