CoolFace
Modelpublic

raghadOmar/whisper-small-ar

sourceHugging Faceapache-2.0updated 2y agoView on Hugging Face
0likes38downloads
Model Card

<!-- 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. -->

Zolfa-raghadomar

This model is a fine-tuned version of tarteel-ai/whisper-base-ar-quran on the Zolfa Dataset dataset. It achieves the following results on the evaluation set:

  • —Loss: 0.2374
  • —Wer: 14.2857

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: 4
  • —evalbatchsize: 8
  • —seed: 42
  • —optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • —lrschedulertype: linear
  • —lrschedulerwarmup_steps: 5
  • —training_steps: 1000
  • —mixedprecisiontraining: Native AMP

Training results

Training LossEpochStepValidation LossWer
0.06690.69931000.204521.4286
0.0241.39862000.231417.3469
0.00852.09793000.213316.3265
0.00852.79724000.212014.2857
0.00523.49655000.222514.2857
0.00364.19586000.235414.2857
0.00164.89517000.232214.2857
0.00025.59448000.237314.2857
0.00036.29379000.237214.2857
0.00126.993010000.237414.2857

Framework versions

  • —Transformers 4.41.2
  • —Pytorch 2.3.0+cu121
  • —Datasets 2.19.2
  • —Tokenizers 0.19.1