Whisper Small Tamil (Saaras-style)
This model is a fine-tuned version of openai/whisper-small on the abar-uwc/tamil-common-voice_v21 dataset. It achieves the following results on the evaluation set:
- Loss: 0.5868
- Wer: 58.1395
- Cer: 19.4737
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: 8
- eval_batch_size: 16
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED 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: 50
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer | Cer |
|---|---|---|---|---|---|
| 2.4813 | 1.9231 | 25 | 0.9838 | 58.7209 | 15.9211 |
| 1.2182 | 3.8462 | 50 | 0.5868 | 58.1395 | 19.4737 |
Framework versions
- Transformers 5.12.1
- Pytorch 2.10.0+cu128
- Datasets 5.0.0
- Tokenizers 0.22.2