whisper-medium-finetuned-maghreb-dialect
This model is a fine-tuned version of openai/whisper-medium on the None dataset. It achieves the following results on the evaluation set:
- Loss: 3.2581
- Wer: 89.8015
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: 2
- eval_batch_size: 2
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 16
- optimizer: Use OptimizerNames.ADAMW_BNB 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: 500
- training_steps: 2000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 20.1548 | 2.0 | 500 | 3.4892 | 95.8765 |
| 18.5662 | 4.0 | 1000 | 3.2821 | 89.8863 |
| 17.8235 | 6.0 | 1500 | 3.2581 | 89.8015 |
| 17.4684 | 8.0 | 2000 | 3.2533 | 90.6330 |
Framework versions
- PEFT 0.15.0
- Transformers 4.50.1
- Pytorch 2.6.0+cu126
- Datasets 3.4.1
- Tokenizers 0.21.1
- Downloads last month
- 35
Inference Providers
NEW
This model isn't deployed by any Inference Provider.
🙋
Ask for provider support
HF Inference deployability: The model has no pipeline_tag.
Model tree for Baraa123R/whisper-medium-finetuned-maghreb-dialect
Base model
openai/whisper-medium