whisper-small-urdu-english-balti
This model is a fine-tuned version of openai/whisper-small on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.5861
- Wer: 0.2550
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: 0.0001
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 200
- num_epochs: 5
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.3202 | 1.2232 | 200 | 0.5730 | 0.3219 |
| 0.1494 | 2.4465 | 400 | 0.6214 | 0.2936 |
| 0.0569 | 3.6697 | 600 | 0.6321 | 0.2825 |
| 0.0128 | 4.8930 | 800 | 0.5861 | 0.2550 |
Framework versions
- Transformers 4.45.0
- Pytorch 2.11.0+cu128
- Datasets 4.0.0
- Tokenizers 0.20.3