Whisper Small Pashto - Augmented
This model is a fine-tuned version of openai/whisper-small on the google/fleurs dataset. It achieves the following results on the evaluation set:
- Loss: 0.6979
- Wer: 53.6244
- Cer: 22.6847
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: 2
- 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: 30
- training_steps: 300
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer | Cer |
|---|---|---|---|---|---|
| 0.9683 | 1.19 | 100 | 0.8812 | 139.3765 | 131.6166 |
| 0.6848 | 2.38 | 200 | 0.7543 | 145.9973 | 151.3369 |
| 0.5548 | 3.57 | 300 | 0.6979 | 53.6244 | 22.6847 |
Framework versions
- Transformers 4.26.0.dev0
- Pytorch 1.13.1+cu117
- Datasets 2.8.1.dev0
- Tokenizers 0.13.2
- Downloads last month
- 8
Dataset used to train ihanif/whisper_small_ps_augmented
Evaluation results
- Wer on google/fleursself-reported53.624