WhisperSmallMarathi - Melroy Pereira
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: 0.4587
- Wer: 44.0719
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: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- training_steps: 4000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.0596 | 4.07 | 1000 | 0.2856 | 45.0132 |
| 0.0048 | 8.13 | 2000 | 0.3908 | 44.7489 |
| 0.0005 | 12.2 | 3000 | 0.4386 | 43.8012 |
| 0.0002 | 16.26 | 4000 | 0.4587 | 44.0719 |
Framework versions
- Transformers 4.36.0.dev0
- Pytorch 2.1.1+cu118
- Datasets 2.15.0
- Tokenizers 0.15.0
- Downloads last month
- 8