Whisper tiny Canadian English
This model is a fine-tuned version of openai/whisper-tiny on the Canadian English dataset. It achieves the following results on the evaluation set:
- Loss: 0.5355
- Wer: 23.0527
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: 3.75e-05
- train_batch_size: 32
- eval_batch_size: 64
- 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: 50
- training_steps: 1000
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.1764 | 1.5873 | 100 | 0.4666 | 21.6365 |
| 0.0619 | 3.1746 | 200 | 0.5085 | 22.9740 |
| 0.0324 | 4.7619 | 300 | 0.5201 | 22.6331 |
| 0.0221 | 6.3492 | 400 | 0.5164 | 23.2887 |
| 0.0167 | 7.9365 | 500 | 0.5290 | 23.5510 |
| 0.0126 | 9.5238 | 600 | 0.5123 | 22.3446 |
| 0.0099 | 11.1111 | 700 | 0.5490 | 24.1542 |
| 0.0080 | 12.6984 | 800 | 0.5347 | 23.6035 |
| 0.0058 | 14.2857 | 900 | 0.5326 | 23.0003 |
| 0.0102 | 15.8730 | 1000 | 0.5355 | 23.0527 |
Framework versions
- Transformers 5.23.0.dev0
- Pytorch 2.11.0+cu130
- Datasets 5.1.0
- Tokenizers 0.23.3