Whisper Small En 3
This model is a fine-tuned version of openai/whisper-small on the Common Voice 3.0 dataset. It achieves the following results on the evaluation set:
- Loss: 0.5263
- Wer: 103.0474
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: Adam with betas=(0.9,0.999) and epsilon=1e-08
- 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 |
|---|---|---|---|---|
| 0.7717 | 1.34 | 1000 | 0.3452 | 49.7815 |
| 0.4884 | 2.67 | 2000 | 0.3808 | 61.0810 |
| 0.4106 | 4.01 | 3000 | 0.4805 | 93.7648 |
| 0.2197 | 5.34 | 4000 | 0.5263 | 103.0474 |
Framework versions
- Transformers 4.39.3
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2
- Downloads last month
- 7