whisper-large-v2-ar-resturant-12.1
This model is a fine-tuned version of openai/whisper-small on the heikal/arabic_call_splitted_8,9 and 10 dataset. It achieves the following results on the evaluation set:
- Loss: 1.1177
- Wer: 60.1614
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: 16
- eval_batch_size: 8
- seed: 42
- optimizer: Use 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_steps: 250
- training_steps: 500
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.3032 | 5.5556 | 250 | 0.9078 | 62.2507 |
| 0.0155 | 11.1111 | 500 | 1.1177 | 60.1614 |
Framework versions
- Transformers 4.47.1
- Pytorch 2.5.1+cu121
- Datasets 3.2.0
- Tokenizers 0.21.0
- Downloads last month
- 83
Inference Providers
NEW
This model is not currently available via any of the supported third-party Inference Providers, and
the model is not deployed on the HF Inference API.
Model tree for heikal/whisper-large-v2-ar-resturant-12.1
Base model
openai/whisper-small