whisper-small-arabic-finetuned-on-halabi_daataset_with-diacritics-2
This model is a fine-tuned version of openai/whisper-small on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.7378
- Wer: 0.7221
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: 16
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 32
- 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: 200
- training_steps: 1000
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.0504 | 3.5133 | 200 | 0.7435 | 0.7221 |
| 0.0138 | 7.0177 | 400 | 0.9074 | 0.7135 |
| 0.0049 | 10.5310 | 600 | 1.1826 | 0.7156 |
| 0.0013 | 14.0354 | 800 | 1.1966 | 0.7156 |
| 0.0008 | 17.5487 | 1000 | 1.1947 | 0.7163 |
Framework versions
- Transformers 4.47.0.dev0
- Pytorch 2.5.1
- Datasets 3.1.0
- Tokenizers 0.20.3