Whisper Small Te - Prashanth Kattoju
This model is a fine-tuned version of openai/whisper-small on the Common Voice 17 dataset. It achieves the following results on the evaluation set:
- Loss: 0.6916
- Wer Ortho: 88.4615
- Wer: 37.5458
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: 500
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer Ortho | Wer |
|---|---|---|---|---|---|
| 0.0016 | 71.4286 | 500 | 0.6916 | 88.4615 | 37.5458 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.4.1+cu121
- Datasets 3.0.1
- Tokenizers 0.19.1
- Downloads last month
- 1
Model tree for kattojuprashanth238/whisper-small-te
Base model
openai/whisper-smallDataset used to train kattojuprashanth238/whisper-small-te
Evaluation results
- Wer on Common Voice 17test set self-reported37.546