Whisper tiny Spanish
This model is a fine-tuned version of openai/whisper-tiny on the Spanish English dataset. It achieves the following results on the evaluation set:
- Loss: 0.2561
- Wer: 11.5672
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: 2
- eval_batch_size: 8
- seed: 42
- 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: 500
- training_steps: 3000
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.4137 | 0.4864 | 500 | 0.2905 | 13.2090 |
| 0.2646 | 0.9728 | 1000 | 0.2671 | 12.2886 |
| 0.1729 | 1.4591 | 1500 | 0.2611 | 12.4876 |
| 0.1360 | 1.9455 | 2000 | 0.2528 | 11.5423 |
| 0.0402 | 2.4319 | 2500 | 0.2628 | 12.2637 |
| 0.0596 | 2.9183 | 3000 | 0.2561 | 11.5672 |
Framework versions
- Transformers 5.23.0.dev0
- Pytorch 2.11.0+cu130
- Datasets 5.1.0
- Tokenizers 0.23.3