README.md

metadata

library_name: transformers
license: apache-2.0
base_model: openai/whisper-large-v3-turbo
tags:
  - generated_from_trainer
datasets:
  - common_voice_11_0
metrics:
  - wer
model-index:
  - name: whisper-large-v3-turbo-arabic
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: common_voice_11_0
          type: common_voice_11_0
          config: ar
          split: test[:500]
          args: ar
        metrics:
          - name: Wer
            type: wer
            value: 31.1455360782715

whisper-large-v3-turbo-arabic

This model is a fine-tuned version of openai/whisper-large-v3-turbo on the common_voice_11_0 dataset. It achieves the following results on the evaluation set:

• Loss: 0.4623
• Wer Ortho: 51.0187
• Wer: 31.1455

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: 16
• eval_batch_size: 16
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: constant_with_warmup
• lr_scheduler_warmup_steps: 30
• training_steps: 100
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer Ortho	Wer
0.3383	0.0416	100	0.4623	51.0187	31.1455

Framework versions

• Transformers 4.45.1
• Pytorch 2.4.1+cu121
• Datasets 3.0.1
• Tokenizers 0.20.0