<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
Urdu_Based_ASR_Model_FYP
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: 0.0030
- Wer: 93.0849
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: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 100
- training_steps: 700
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 1.2479 | 2.27 | 100 | 1.0445 | 103.8776 |
| 0.3529 | 4.55 | 200 | 0.2966 | 70.4653 |
| 0.148 | 6.82 | 300 | 0.1006 | 54.3300 |
| 0.047 | 9.09 | 400 | 0.0274 | 52.7574 |
| 0.0101 | 11.36 | 500 | 0.0099 | 65.1659 |
| 0.0041 | 13.64 | 600 | 0.0039 | 84.2309 |
| 0.0033 | 15.91 | 700 | 0.0030 | 93.0849 |
Framework versions
- Transformers 4.30.0.dev0
- Pytorch 2.0.1+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3
