Asma50AA/trail-with-517-whisper-small-ar

<!-- 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. -->

trail-with-517-whisper-small-ar

This model is a fine-tuned version of openai/whisper-small on an unknown dataset. It achieves the following results on the evaluation set:

• —eval_loss: 0.7954
• —eval_wer: 46.2178
• —eval_runtime: 160.3806
• —evalsamplesper_second: 0.935
• —evalstepsper_second: 0.118
• —epoch: 11.0
• —step: 363

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
• —trainbatchsize: 16
• —evalbatchsize: 8
• —seed: 42
• —optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• —lrschedulertype: linear
• —lrschedulerwarmup_steps: 500
• —num_epochs: 15
• —mixedprecisiontraining: Native AMP

Framework versions

• —Transformers 4.38.1
• —Pytorch 2.1.0+cu121
• —Datasets 2.18.0
• —Tokenizers 0.15.2