Whisper Tiny Indonesian - Chee Li
This model is a fine-tuned version of openai/whisper-tiny on the Google Fleurs dataset. It achieves the following results on the evaluation set:
- Loss: 1.1541
- Wer: 61.5100
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: 16
- eval_batch_size: 8
- seed: 42
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- training_steps: 5000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.3796 | 4.4643 | 1000 | 0.7934 | 60.0473 |
| 0.097 | 8.9286 | 2000 | 0.8975 | 61.0446 |
| 0.0167 | 13.3929 | 3000 | 1.0411 | 61.1998 |
| 0.0057 | 17.8571 | 4000 | 1.1252 | 62.8694 |
| 0.0044 | 22.3214 | 5000 | 1.1541 | 61.5100 |
Framework versions
- Transformers 4.46.2
- Pytorch 2.3.1+cu121
- Datasets 2.20.0
- Tokenizers 0.20.1
- Downloads last month
- 88
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 CheeLi03/whisper-base-he-puct-5k
Base model
openai/whisper-tiny