Whisper Small gl
This model is a fine-tuned version of openai/whisper-small on the Common Voice 17.0 dataset. It achieves the following results on the evaluation set:
- Loss: 1.9699
- Wer: 15.4306
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: 64
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- training_steps: 5000
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.1844 | 1.8182 | 1000 | 1.6681 | 13.8720 |
| 0.0708 | 3.6364 | 2000 | 1.7869 | 13.2062 |
| 0.0351 | 5.4545 | 3000 | 1.8885 | 14.2740 |
| 0.0196 | 7.2727 | 4000 | 1.9333 | 15.7785 |
| 0.0144 | 9.0909 | 5000 | 1.9699 | 15.4306 |
Framework versions
- Transformers 4.42.0.dev0
- Pytorch 2.3.0+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1