wh_med_iv_30_70_flattened_indic_voices_52553__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: 0.3223
- Global Wer: 38.2963
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 |
|---|---|---|---|---|
| 1.5657 | 0.0158 | 50 | 1.3639 | 59.8234 |
| 0.8758 | 0.0317 | 100 | 0.7776 | 50.0967 |
| 0.4615 | 0.0475 | 150 | 0.4275 | 47.9791 |
| 0.4872 | 0.0633 | 200 | 0.3920 | 44.7281 |
| 0.3992 | 0.0792 | 250 | 0.3864 | 46.0241 |
| 0.3770 | 0.0950 | 300 | 0.3627 | 41.5737 |
| 0.3336 | 0.1108 | 350 | 0.3476 | 41.8329 |
| 0.3481 | 0.1267 | 400 | 0.3347 | 38.9157 |
| 0.3058 | 0.1425 | 450 | 0.3315 | 38.9553 |
| 0.3360 | 0.1583 | 500 | 0.3223 | 38.2963 |
Framework versions
- Transformers 5.0.0.dev0
- Pytorch 2.9.0+cu126
- Datasets 3.6.0
- Tokenizers 0.22.2