Whisper Medium Urdu - Hassaan Butt
This model is a fine-tuned version of openai/whisper-medium on the common voice dataset. It achieves the following results on the evaluation set:
- Wer: 32.0
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: 8
- 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: 3000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.283800 | 2.92 | 1000 | 0.466280 | 51.433879 |
| 0.090300 | 5.85 | 2000 | 0.448847 | 33.646813 |
| 0.036666 | 8.77 | 3000 | 0.420809 | 32.035004 |
Framework versions
- Transformers 4.26.0.dev0
- Pytorch 1.11.0+cu113
- Datasets 11.0
- Tokenizers 0.13.2
- Downloads last month
- 6
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.