Whisper Small Dv
This model is a fine-tuned version of openai/whisper-small on the Common Voice 13 Dv dataset. It achieves the following results on the evaluation set:
- Loss: 0.1731
- Wer Ortho: 63.0545
- Wer: 13.5793
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: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: constant_with_warmup
- lr_scheduler_warmup_steps: 50
- training_steps: 500
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer Ortho | Wer |
|---|---|---|---|---|---|
| 0.1211 | 1.6287 | 500 | 0.1731 | 63.0545 | 13.5793 |
Framework versions
- Transformers 4.47.1
- Pytorch 2.5.1+cu121
- Datasets 3.2.0
- Tokenizers 0.21.0
- Downloads last month
- 1
Model tree for Sravana/whisper-small-dv
Base model
openai/whisper-smallDataset used to train Sravana/whisper-small-dv
Evaluation results
- Wer on Common Voice 13 Dvtest set self-reported13.579