whisper-tiny-en-us
This model is a fine-tuned version of openai/whisper-tiny on the PolyAI/minds14 dataset. It achieves the following results on the evaluation set:
- Loss: 0.7049
- Wer Ortho: 0.3291
- Wer: 0.3288
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: 16
- 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: constant_with_warmup
- lr_scheduler_warmup_steps: 50
- training_steps: 500
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer Ortho | Wer |
|---|---|---|---|---|---|
| 0.0006 | 17.8571 | 500 | 0.7049 | 0.3291 | 0.3288 |
Framework versions
- Transformers 4.48.0.dev0
- Pytorch 2.6.0+cu126
- Datasets 3.2.0
- Tokenizers 0.21.0
- Downloads last month
- -
Model tree for f0ghedgeh0g/whisper-tiny-en-us
Base model
openai/whisper-tinyDataset used to train f0ghedgeh0g/whisper-tiny-en-us
Evaluation results
- Wer on PolyAI/minds14self-reported0.329