Whisper Small Ja - vlzcrz
This model is a fine-tuned version of openai/whisper-small on the Common Voice 17.0 dataset. It achieves the following results on the evaluation set:
- Loss: 0.5403
- Wer: 82.7711
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
- optimizer: Use OptimizerNames.ADAMW_TORCH 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
- training_steps: 4000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.3514 | 0.9814 | 1000 | 0.5294 | 83.8224 |
| 0.2439 | 1.9627 | 2000 | 0.5107 | 84.8109 |
| 0.1145 | 2.9441 | 3000 | 0.5191 | 81.8296 |
| 0.066 | 3.9254 | 4000 | 0.5403 | 82.7711 |
Framework versions
- Transformers 4.48.1
- Pytorch 2.5.1+cu121
- Datasets 3.2.0
- Tokenizers 0.21.0