openai/whisper-medium-nepali
This model is a fine-tuned version of shripadbhat/whisper-medium-hi on the Common Voice 11.0 dataset. It achieves the following results on the evaluation set:
- Loss: 0.8578
- Wer: 34.1463
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: 8
- seed: 42
- gradient_accumulation_steps: 8
- 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: 40
- training_steps: 20
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.0673 | 20.0 | 20 | 0.8578 | 34.1463 |
Framework versions
- Transformers 4.26.0.dev0
- Pytorch 1.11.0
- Datasets 2.8.1.dev0
- Tokenizers 0.12.1