Whisper Small tr - Kshitiz-Khandelwal
This model is a fine-tuned version of openai/whisper-small on the Common Voice 11.0 dataset. It achieves the following results on the evaluation set:
- Loss: 0.2475
- Wer: 22.3516
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
- 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: 500
- training_steps: 1500
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.2152 | 0.22 | 500 | 0.2900 | 25.5283 |
| 0.1656 | 0.44 | 1000 | 0.2639 | 23.8575 |
| 0.1853 | 0.66 | 1500 | 0.2475 | 22.3516 |
Framework versions
- Transformers 4.25.0.dev0
- Pytorch 1.12.1+cu113
- Datasets 2.7.1
- Tokenizers 0.13.2