whisper-tiny-khmer
This model is a fine-tuned version of openai/whisper-tiny on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.0702
- Cer: 21.3240
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: 3.75e-05
- train_batch_size: 16
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 32
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED 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: 200
- training_steps: 3000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Cer |
|---|---|---|---|---|
| 0.6746 | 0.4847 | 500 | 0.3200 | 44.1463 |
| 0.2546 | 0.9695 | 1000 | 0.1280 | 27.2033 |
| 0.1639 | 1.4537 | 1500 | 0.0965 | 23.0473 |
| 0.1559 | 1.9384 | 2000 | 0.0815 | 21.5974 |
| 0.1056 | 2.4227 | 2500 | 0.0744 | 21.2300 |
| 0.1034 | 2.9074 | 3000 | 0.0702 | 21.3240 |
Framework versions
- Transformers 5.14.1
- Pytorch 2.8.0+cu128
- Datasets 5.0.0
- Tokenizers 0.22.2