comprend-la-dunia-quran
This model is a fine-tuned version of openai/whisper-small on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.0489
- Wer: 14.4784
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: 4
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 8
- 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: 100
- num_epochs: 5
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.2291 | 1.0 | 741 | 0.0600 | 20.4400 |
| 0.2048 | 2.0 | 1482 | 0.0537 | 18.1689 |
| 0.1389 | 3.0 | 2223 | 0.0471 | 15.0461 |
| 0.1246 | 4.0 | 2964 | 0.0476 | 14.1945 |
| 0.0786 | 5.0 | 3705 | 0.0489 | 14.4784 |
Framework versions
- Transformers 5.0.0
- Pytorch 2.11.0+cu128
- Datasets 4.0.0
- Tokenizers 0.22.2
- Downloads last month
- 8
Model tree for SmokePearl/comprend-la-dunia-quran
Base model
openai/whisper-small