deepdml's picture
Upload README.md with huggingface_hub
6a68322 verified
metadata
language:
  - ar
license: apache-2.0
base_model: openai/whisper-small
tags:
  - generated_from_trainer
datasets:
  - UBC-NLP/Casablanca
  - ymoslem/MediaSpeech
  - mozilla-foundation/common_voice_17_0
  - google/fleurs
metrics:
  - wer
model-index:
  - name: Whisper Small ar
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: Common Voice 17.0
          type: UBC-NLP/Casablanca
          config: ar
          split: test
          args: ar
        metrics:
          - name: Wer
            type: wer
            value: 26.536160957041872

Whisper Small ar

This model is a fine-tuned version of openai/whisper-small on the Common Voice 17.0 dataset. It achieves the following results on the evaluation set:

  • Loss: 2.2980
  • Wer: 26.5362

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: 64
  • 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: 5000

Training results

Training Loss Epoch Step Validation Loss Wer
0.2564 0.2 1000 1.8598 30.7045
0.061 0.4 2000 2.1891 28.2575
0.0368 0.6 3000 2.2045 26.3524
0.0262 0.8 4000 2.4023 26.1855
0.0128 1.0 5000 2.2980 26.5362

Framework versions

  • Transformers 4.42.0.dev0
  • Pytorch 2.3.0+cu121
  • Datasets 2.19.1
  • Tokenizers 0.19.1

Citation

@misc{deepdml/whisper-small-ar-mix-norm,
      title={Fine-tuned Whisper small ASR model for speech recognition in Arabic},
      author={Jimenez, David},
      howpublished={\url{https://huggingface.co/deepdml/whisper-small-ar-mix-norm}},
      year={2025}
    }