Whisper Tiny Thai Punctuation 5k - 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: 0.7730
- Wer: 123.4861
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 |
|---|---|---|---|---|
| 0.2888 | 5.2356 | 1000 | 0.6095 | 131.7739 |
| 0.0918 | 10.4712 | 2000 | 0.6100 | 119.5203 |
| 0.0229 | 15.7068 | 3000 | 0.6838 | 122.1325 |
| 0.0069 | 20.9424 | 4000 | 0.7521 | 121.0639 |
| 0.0049 | 26.1780 | 5000 | 0.7730 | 123.4861 |
Framework versions
- Transformers 4.46.2
- Pytorch 2.3.1+cu121
- Datasets 2.20.0
- Tokenizers 0.20.3
- Downloads last month
- 87
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-tiny-th-puct-5k
Base model
openai/whisper-tiny