Whisper Base Persian Iranian
This model is a fine-tuned version of arun100/whisper-base-fa-1 on the google/fleurs fa_ir dataset. It achieves the following results on the evaluation set:
- Loss: 0.5030
- Wer: 41.2338
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-06
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- training_steps: 5000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.1284 | 86.0 | 1000 | 0.5030 | 41.2338 |
| 0.0179 | 173.0 | 2000 | 0.5767 | 41.6119 |
| 0.0074 | 260.0 | 3000 | 0.6171 | 41.4478 |
| 0.0047 | 347.0 | 4000 | 0.6419 | 42.1791 |
| 0.0039 | 434.0 | 5000 | 0.6517 | 41.9751 |
Framework versions
- Transformers 4.37.0.dev0
- Pytorch 2.1.2+cu121
- Datasets 2.16.2.dev0
- Tokenizers 0.15.0