Whisper base ar - Mohamed Ahmed-Mahmoud Nasser
This model is a fine-tuned version of openai/whisper-base on the private dataset. It achieves the following results on the evaluation set:
- eval_loss: 0.0850
- eval_wer: 17.2414
- eval_runtime: 7.2317
- eval_samples_per_second: 4.01
- eval_steps_per_second: 0.553
- epoch: 6.5274
- step: 2500
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: 500
- training_steps: 3000
- mixed_precision_training: Native AMP
Framework versions
- Transformers 4.49.0
- Pytorch 2.5.1+cu121
- Datasets 3.3.2
- Tokenizers 0.21.0
- Downloads last month
- 32
Inference Providers
NEW
This model is not currently available via any of the supported Inference Providers.
Model tree for Mohamed2210/whisper-base-ar-v1
Base model
openai/whisper-base