whisper-base-arabic-base-v2.1
This model is a fine-tuned version of openai/whisper-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.5048
- Wer: 0.5558
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-05
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.01
- num_epochs: 4
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.7955 | 1.0 | 1476 | 0.6025 | 0.6847 |
| 0.6122 | 2.0 | 2952 | 0.5387 | 0.6075 |
| 0.5065 | 3.0 | 4428 | 0.5126 | 0.5567 |
| 0.4651 | 4.0 | 5904 | 0.5048 | 0.5558 |
Framework versions
- Transformers 4.53.3
- Pytorch 2.6.0+cu124
- Datasets 3.6.0
- Tokenizers 0.21.2
- Downloads last month
- 9
Model tree for shredder-31/whisper-base-arabic-v2.1
Base model
openai/whisper-base