Whisper Small Urdu - Muhammad Ahmad
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: 0.5270
- Wer Ortho: 56.1224
- Wer: 52.7675
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: 700
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer Ortho | Wer |
|---|---|---|---|---|---|
| 0.2885 | 1.0753 | 500 | 0.5270 | 56.1224 | 52.7675 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.5.0+cu121
- Datasets 3.1.0
- Tokenizers 0.19.1
- Downloads last month
- 1
Model tree for ahmadmac/whisper-small-urdu
Base model
openai/whisper-smallDataset used to train ahmadmac/whisper-small-urdu
Evaluation results
- Wer on Common Voice 13test set self-reported52.767