ReejaNoor/whisper-base-ar-restaurant

<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->

whisper-base-ar-restaurant

This model is a fine-tuned version of openai/whisper-base on the None dataset. It achieves the following results on the evaluation set:

• —eval_loss: 0.0233
• —eval_runtime: 13.6186
• —evalsamplesper_second: 7.343
• —evalstepsper_second: 0.514
• —epoch: 34.4956
• —step: 1000

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: 2e-05
• —trainbatchsize: 8
• —evalbatchsize: 16
• —seed: 42
• —gradientaccumulationsteps: 4
• —totaltrainbatch_size: 32
• —optimizer: Use OptimizerNames.ADAMWTORCHFUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• —lrschedulertype: linear
• —lrschedulerwarmup_steps: 500
• —training_steps: 4000
• —mixedprecisiontraining: Native AMP

Framework versions

• —Transformers 4.57.1
• —Pytorch 2.8.0+cu126
• —Datasets 4.4.2
• —Tokenizers 0.22.1