whisper-tiny-eng-transliterated-nep
This model is a fine-tuned version of openai/whisper-tiny.en on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.7625
- Wer: 48.5073
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: 5e-05
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 16
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 200
- training_steps: 500
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 1.9083 | 3.0121 | 250 | 0.8480 | 55.6012 |
| 0.248 | 6.0242 | 500 | 0.7625 | 48.5073 |
Framework versions
- Transformers 4.47.1
- Pytorch 2.4.1+cu121
- Datasets 3.2.0
- Tokenizers 0.21.0