whisper-medium_indic_voices_68116_15_100_1e-4_None_hinglish_mixed_scripts_FT
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: 0.4254
- Global Wer: 30.0209
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: 0.0001
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 32
- 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: 500
- num_epochs: 100
Training results
| Training Loss | Epoch | Step | Validation Loss | Global Wer |
|---|---|---|---|---|
| 0.9749 | 1.0 | 432 | 0.4270 | 37.0019 |
| 0.6138 | 2.0 | 864 | 0.4162 | 31.1753 |
| 0.4208 | 3.0 | 1296 | 0.4254 | 30.0209 |
| 0.3070 | 4.0 | 1728 | 0.4415 | 31.9574 |
| 0.2355 | 5.0 | 2160 | 0.4720 | 31.4045 |
| 0.1925 | 6.0 | 2592 | 0.4865 | 31.9001 |
Framework versions
- Transformers 5.0.0.dev0
- Pytorch 2.9.0+cu126
- Datasets 3.6.0
- Tokenizers 0.22.2