Whisper Small Nepali Finetune - Devinit
This model is a fine-tuned version of openai/whisper-small on the Common Voice 13 dataset. It achieves the following results on the evaluation set:
- Loss: 0.7953
- Wer Ortho: 67.0236
- Wer: 34.2593
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: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: constant_with_warmup
- lr_scheduler_warmup_steps: 50
- training_steps: 500
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer Ortho | Wer |
|---|---|---|---|---|---|
| 0.0003 | 35.71 | 500 | 0.7953 | 67.0236 | 34.2593 |
Framework versions
- Transformers 4.34.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.14.1
- Downloads last month
- 3
Model tree for alex-miller/whisper-small-np
Base model
openai/whisper-smallDataset used to train alex-miller/whisper-small-np
Evaluation results
- Wer on Common Voice 13test set self-reported34.259