Whisper Small Ori vi
This model is a fine-tuned version of openai/whisper-small on the Common Voice 11.0 dataset. It achieves the following results on the evaluation set:
- Loss: 0.7270
- Wer: 20.0736
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 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 |
|---|---|---|---|---|
| 0.1721 | 2.2222 | 1000 | 0.4944 | 18.9478 |
| 0.032 | 4.4444 | 2000 | 0.5955 | 21.0508 |
| 0.0041 | 6.6667 | 3000 | 0.6888 | 19.9391 |
| 0.0014 | 8.8889 | 4000 | 0.7270 | 20.0736 |
Framework versions
- Transformers 4.46.1
- Pytorch 2.4.0
- Datasets 3.0.2
- Tokenizers 0.20.0