openai/whisper-small-Urdu
This model is a fine-tuned version of Zaid/whisper-small-commonvoice on the Common Voice 11.0 dataset. It achieves the following results on the evaluation set:
- Loss: 0.5881
- Wer: 44.2387
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: 2
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 16
- total_train_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 40
- training_steps: 200
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.5993 | 0.5 | 100 | 0.6257 | 37.9294 |
| 0.352 | 1.35 | 200 | 0.5881 | 44.2387 |
Framework versions
- Transformers 4.26.0.dev0
- Pytorch 1.11.0
- Datasets 2.1.0
- Tokenizers 0.12.1