Edit model card

Whisper Small ar - Mohammed Nasri

This model is a fine-tuned version of openai/whisper-small on the Common Voice 11.0 dataset. It achieves the following results on the evaluation set:

  • Loss: 0.1945
  • Wer: 17.3068

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: 8
  • eval_batch_size: 8
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_steps: 500
  • training_steps: 6000
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Wer
0.0669 0.05 1000 0.2389 21.1529
0.0532 0.1 2000 0.2350 20.0492
0.0647 0.16 3000 0.2214 19.3772
0.096 0.21 4000 0.2139 18.7315
0.0802 0.26 5000 0.2038 17.8567
0.1331 0.31 6000 0.1945 17.3068

Framework versions

  • Transformers 4.28.0.dev0
  • Pytorch 1.12.1
  • Datasets 2.10.1
  • Tokenizers 0.13.2
Downloads last month
3

Dataset used to train MohammedNasri/whisper-small-AR

Evaluation results