Whisper tiny Indian
This model is a fine-tuned version of openai/whisper-tiny on the Indian English dataset. It achieves the following results on the evaluation set:
- Loss: 0.2614
- Wer: 9.2319
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
- 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: 0.25
- num_epochs: 2
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.3800 | 0.5 | 429 | 0.3029 | 10.8283 |
| 0.3449 | 1.0 | 858 | 0.2774 | 9.7590 |
| 0.1384 | 1.5 | 1287 | 0.2648 | 9.6386 |
| 0.1788 | 2.0 | 1716 | 0.2614 | 9.2319 |
Framework versions
- Transformers 5.22.0.dev0
- Pytorch 2.11.0+cu130
- Datasets 5.1.0
- Tokenizers 0.23.3