Whisper-Small-Ar-Tashkeel-Dev - AzeemX
This model is a fine-tuned version of MohammedNasri/whisper_small_ar_augmentation on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.1175
- Wer: 108.2882
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: 4
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- training_steps: 1000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.115 | 1.0323 | 1000 | 0.1175 | 108.2882 |
Framework versions
- Transformers 4.45.2
- Pytorch 2.3.1
- Datasets 3.0.1
- Tokenizers 0.20.0
- Downloads last month
- 15
Inference Providers
NEW
This model is not currently available via any of the supported Inference Providers.
Model tree for WajeehAzeemX/Whisper-Small-Ar-Tashkeel-Dev-1000
Base model
MohammedNasri/whisper_small_ar_augmentation