Whisper Small Hi
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: 0.4802
- Wer: 33.0441
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: 6000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.0884 | 2.44 | 1000 | 0.2931 | 35.1139 |
| 0.0213 | 4.89 | 2000 | 0.3515 | 34.0303 |
| 0.0025 | 7.33 | 3000 | 0.4181 | 33.0399 |
| 0.0007 | 9.78 | 4000 | 0.4473 | 32.7817 |
| 0.0001 | 12.22 | 5000 | 0.4737 | 32.9764 |
| 0.0001 | 14.67 | 6000 | 0.4802 | 33.0441 |
Framework versions
- Transformers 4.39.3
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2
- Downloads last month
- 5