README.md

metadata

language:
  - ar
license: apache-2.0
base_model: openai/whisper-medium
tags:
  - generated_from_trainer
datasets:
  - Arbi-Houssem/comondov
metrics:
  - wer
model-index:
  - name: Whisper Tunisien
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: comondov
          type: Arbi-Houssem/comondov
          args: 'config: ar, split: test'
        metrics:
          - name: Wer
            type: wer
            value: 106.18181818181817

Whisper Tunisien

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

• Loss: 3.2714
• Wer: 106.1818

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: 1000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.2223	5.2083	500	2.8313	106.8364
0.0126	10.4167	1000	3.2714	106.1818

Framework versions

• Transformers 4.42.0.dev0
• Pytorch 2.3.0+cu121
• Datasets 2.19.2
• Tokenizers 0.19.1