whisperDAR / README.md
hamzabennz's picture
End of training
7051b76 verified
metadata
language:
  - ar
license: apache-2.0
base_model: openai/whisper-small
tags:
  - hf-asr-leaderboard
  - generated_from_trainer
datasets:
  - team4/8dretna_daridja
metrics:
  - wer
model-index:
  - name: whisperDAR
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: 8dretna_daridja
          type: team4/8dretna_daridja
          args: 'split: test'
        metrics:
          - name: Wer
            type: wer
            value: 94.27182780767228

whisperDAR

This model is a fine-tuned version of openai/whisper-small on the 8dretna_daridja dataset. It achieves the following results on the evaluation set:

  • Loss: 4.6653
  • Wer: 94.2718

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: 10
  • 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: 5
  • training_steps: 5
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Wer
4.3481 0.0107 5 4.6653 94.2718

Framework versions

  • Transformers 4.42.0.dev0
  • Pytorch 2.1.2+cu121
  • Datasets 2.19.1
  • Tokenizers 0.19.1