Whisper Small Id - Fine Tuned - Revised
This model is a fine-tuned version of openai/whisper-small on the Common Voice 13 dataset.
It achieves the following results on the evaluation set:
- Loss: 0.3528
- Wer Ortho: 22.8496
- Wer: 18.4708
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: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: constant_with_warmup
- lr_scheduler_warmup_steps: 50
- training_steps: 1000
- mixed_precision_training: Native AMP
Training results
| Training Loss |
Epoch |
Step |
Validation Loss |
Wer Ortho |
Wer |
| 0.3546 |
0.7911 |
250 |
0.3433 |
23.8195 |
18.6421 |
| 0.1621 |
1.5823 |
500 |
0.3325 |
23.2594 |
18.9171 |
| 0.058 |
2.3734 |
750 |
0.3483 |
23.1274 |
18.0966 |
| 0.0265 |
3.1646 |
1000 |
0.3528 |
22.8496 |
18.4708 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.3.0+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1
