whisper-burmese-myanify
This model is a fine-tuned version of tettoewai/whisper-burmese-myanify on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.4011
- Cer: 0.5333
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
- 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: 1500
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Cer |
|---|---|---|---|---|
| 0.0048 | 1.4286 | 250 | 0.3871 | 0.5407 |
| 0.0040 | 2.8571 | 500 | 0.3830 | 0.5418 |
| 0.0014 | 4.2857 | 750 | 0.3918 | 0.5389 |
| 0.0005 | 5.7143 | 1000 | 0.3983 | 0.5357 |
| 0.0001 | 7.1429 | 1250 | 0.3970 | 0.5344 |
| 0.0001 | 8.5714 | 1500 | 0.4011 | 0.5333 |
Framework versions
- Transformers 5.0.0
- Pytorch 2.10.0+cu128
- Datasets 5.0.0
- Tokenizers 0.22.2