Configuration Parsing
Warning:
In adapter_config.json: "peft.task_type" must be a string
Whipser_arabic_adapter
This model is a fine-tuned version of unsloth/whisper-large-v3 on an unknown dataset. It achieves the following results on the evaluation set:
- eval_loss: 1.5822
- eval_wer: 23.2992
- eval_runtime: 960.6359
- eval_samples_per_second: 1.041
- eval_steps_per_second: 0.13
- epoch: 0.0338
- step: 60
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: 0
- gradient_accumulation_steps: 4
- total_train_batch_size: 16
- 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: cosine
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 1
- mixed_precision_training: Native AMP
Framework versions
- PEFT 0.16.0
- Transformers 4.51.3
- Pytorch 2.6.0+cu124
- Datasets 3.6.0
- Tokenizers 0.21.2
- Downloads last month
- -
Inference Providers
NEW
This model isn't deployed by any Inference Provider.
🙋
Ask for provider support