<!-- 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. -->
whisper-small-urdu_bkk
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: 1.1416
- Wer: 54.4035
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: 4000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.8024 | 3.35 | 800 | 0.6546 | 39.5662 |
| 0.1409 | 6.69 | 1600 | 0.8260 | 47.5698 |
| 0.0301 | 10.04 | 2400 | 0.9745 | 47.8208 |
| 0.0074 | 13.39 | 3200 | 1.0855 | 54.9558 |
| 0.0021 | 16.74 | 4000 | 1.1416 | 54.4035 |
Framework versions
- Transformers 4.30.0.dev0
- Pytorch 2.0.1+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3
