wh_l_v3_t_iv_no_lg_id_indic_voices_52031_trial
This model is a fine-tuned version of openai/whisper-large-v3-turbo on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.3913
- Global Wer: 42.2550
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 |
|---|---|---|---|---|
| 0.4455 | 0.0110 | 50 | 0.4740 | 56.7293 |
| 0.4146 | 0.0220 | 100 | 0.4673 | 60.2336 |
| 0.4558 | 0.0330 | 150 | 0.4414 | 54.6978 |
| 0.3726 | 0.0440 | 200 | 0.4034 | 48.4002 |
| 0.3527 | 0.0550 | 250 | 0.4413 | 47.6892 |
| 0.3808 | 0.0660 | 300 | 0.4078 | 43.4738 |
| 0.3825 | 0.0770 | 350 | 0.3941 | 43.1183 |
| 0.4281 | 0.0880 | 400 | 0.3924 | 50.1270 |
| 0.3703 | 0.0990 | 450 | 0.3777 | 46.5211 |
| 0.3258 | 0.1100 | 500 | 0.3913 | 42.2550 |
Framework versions
- Transformers 5.0.0.dev0
- Pytorch 2.9.0+cu126
- Datasets 3.6.0
- Tokenizers 0.22.2