wh_med_iv_30_70_indic_voices_52508__val_finetune_trial
This model is a fine-tuned version of openai/whisper-medium on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.3207
- Global Wer: 38.2831
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: 5e-06
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- optimizer: Use adamw_torch_fused with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: constant_with_warmup
- lr_scheduler_warmup_steps: 50
- training_steps: 500
Training results
| Training Loss | Epoch | Step | Validation Loss | Global Wer |
|---|---|---|---|---|
| 1.5668 | 0.0158 | 50 | 1.3723 | 60.1529 |
| 0.8729 | 0.0317 | 100 | 0.7716 | 49.7540 |
| 0.4610 | 0.0475 | 150 | 0.4255 | 47.5661 |
| 0.4881 | 0.0633 | 200 | 0.3929 | 44.4776 |
| 0.3983 | 0.0792 | 250 | 0.3872 | 46.1427 |
| 0.3774 | 0.0950 | 300 | 0.3605 | 41.0333 |
| 0.3353 | 0.1108 | 350 | 0.3471 | 42.1448 |
| 0.3496 | 0.1267 | 400 | 0.3350 | 38.8103 |
| 0.3062 | 0.1425 | 450 | 0.3332 | 38.9728 |
| 0.3357 | 0.1583 | 500 | 0.3207 | 38.2831 |
Framework versions
- Transformers 5.0.0.dev0
- Pytorch 2.9.0+cu126
- Datasets 3.6.0
- Tokenizers 0.22.2