whisper-small-SIT_05_05_26_1014
This model is a fine-tuned version of Pengwin30/whisper-small-fine-tuned on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.4099
- Wer: 10.0629
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-06
- train_batch_size: 8
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 16
- 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 |
|---|---|---|---|---|
| 7.8413 | 1.0 | 22 | 3.5298 | 12.5786 |
| 6.7653 | 2.0 | 44 | 2.8798 | 9.4340 |
| 4.9996 | 3.0 | 66 | 1.9076 | 9.4340 |
| 2.7251 | 4.0 | 88 | 0.7472 | 9.4340 |
| 0.9442 | 5.0 | 110 | 0.4099 | 10.0629 |
Framework versions
- Transformers 5.0.0
- Pytorch 2.10.0+cu128
- Datasets 2.19.0
- Tokenizers 0.22.2