whisper-small-gu
This model is a fine-tuned version of openai/whisper-small on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.9980
- Wer: 101.5466
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 |
|---|---|---|---|---|
| 1.2455 | 17.5439 | 1000 | 1.2529 | 100.0 |
| 1.0102 | 35.0877 | 2000 | 1.0608 | 105.5149 |
| 0.894 | 52.6316 | 3000 | 1.0094 | 101.7908 |
| 0.8411 | 70.1754 | 4000 | 0.9980 | 101.5466 |
Framework versions
- Transformers 4.47.0
- Pytorch 2.5.1+cu118
- Datasets 3.1.0
- Tokenizers 0.21.0