whisper-small-ha
This model is a fine-tuned version of openai/whisper-small on the common_voice_16_1 dataset. It achieves the following results on the evaluation set:
- Loss: 0.7407
- Wer Ortho: 46.9799
- Wer: 43.7928
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: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: constant_with_warmup
- lr_scheduler_warmup_steps: 50
- training_steps: 1000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer Ortho | Wer |
|---|---|---|---|---|---|
| 0.0742 | 3.18 | 500 | 0.6846 | 48.4180 | 45.0495 |
| 0.0145 | 6.37 | 1000 | 0.7407 | 46.9799 | 43.7928 |
Framework versions
- Transformers 4.39.3
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2