Whisper Small Br - Arzhur Koadek
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: 0.9421
- Wer: 52.2397
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 |
|---|---|---|---|---|
| 0.168 | 3.2468 | 1000 | 0.7951 | 53.9458 |
| 0.0124 | 6.4935 | 2000 | 0.8755 | 51.6273 |
| 0.0016 | 9.7403 | 3000 | 0.9224 | 52.6509 |
| 0.0009 | 12.9870 | 4000 | 0.9421 | 52.2397 |
Framework versions
- Transformers 4.40.1
- Pytorch 2.2.1+cu121
- Datasets 2.19.0
- Tokenizers 0.19.1
- Downloads last month
- 2