Whisper Small Dv - Tashi Phuntsho
This model is a fine-tuned version of openai/whisper-small on the Voice Data dataset. It achieves the following results on the evaluation set:
- Loss: 5.2438
- Wer Ortho: 262.4138
- Wer: 187.7491
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: 5
- training_steps: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer Ortho | Wer |
|---|---|---|---|---|---|
| 5.7882 | 0.0326 | 10 | 5.2438 | 262.4138 | 187.7491 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.4.0+cu121
- Datasets 3.0.0
- Tokenizers 0.19.1
- Downloads last month
- 3
Model tree for Tashi58/whisper-small-dv
Base model
openai/whisper-smallDataset used to train Tashi58/whisper-small-dv
Evaluation results
- Wer on Voice Datatest set self-reported187.749