Configuration Parsing
Warning:
In adapter_config.json: "peft.task_type" must be a string
Whisper Large v3 Thai Finetuned
This model is a fine-tuned version of openai/whisper-large-v3 on the Common Voice 17.0 dataset. It achieves the following results on the evaluation set:
- Loss: 0.1953
- Cer: 49.5719
- Wer: 77.0705
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: 0.0002
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Use paged_adamw_8bit 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
- num_epochs: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Cer | Wer |
|---|---|---|---|---|---|
| 0.158 | 1.0 | 2052 | 0.1361 | 288.0891 | 56.6543 |
| 0.1166 | 2.0 | 4104 | 0.1296 | 232.8857 | 57.0405 |
| 0.0739 | 3.0 | 6156 | 0.1298 | 107.5882 | 42.6799 |
| 0.0467 | 4.0 | 8208 | 0.1370 | 61.4281 | 43.2440 |
| 0.0263 | 5.0 | 10260 | 0.1424 | 69.8588 | 80.9373 |
| 0.012 | 6.0 | 12312 | 0.1607 | 56.1242 | 68.8006 |
| 0.0081 | 7.0 | 14364 | 0.1649 | 130.1459 | 76.1770 |
| 0.0036 | 8.0 | 16416 | 0.1782 | 110.6614 | 116.6100 |
| 0.002 | 9.0 | 18468 | 0.1862 | 50.2801 | 85.8464 |
| 0.0005 | 10.0 | 20520 | 0.1953 | 49.5719 | 77.0705 |
Framework versions
- PEFT 0.14.1.dev0
- Transformers 4.49.0.dev0
- Pytorch 2.5.1+cu124
- Datasets 3.2.0
- Tokenizers 0.21.0
- Downloads last month
- 120
Inference Providers
NEW
This model is not currently available via any of the supported Inference Providers.
The model cannot be deployed to the HF Inference API:
The model has no pipeline_tag.
Model tree for sreyroth/whisper-large-v3-cv17-th-ft-with-lr-1e-3
Base model
openai/whisper-large-v3