README.md

metadata

language:
  - ar
license: apache-2.0
base_model: openai/whisper-large-v3
tags:
  - hf-asr-leaderboard
  - generated_from_trainer
datasets:
  - whitefox123/tashkeel
metrics:
  - wer
model-index:
  - name: Whisper large - tuned
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: CLARtts
          type: whitefox123/tashkeel
          config: default
          split: None
          args: 'config: ar, split: test'
        metrics:
          - name: Wer
            type: wer
            value: 217.9099099099099

Whisper large - tuned

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

• Loss: 0.1346
• Wer: 217.9099

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: 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: 3125
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.0843	1.6	1000	0.1141	248.9730
0.024	3.2	2000	0.1194	274.9189
0.0108	4.8	3000	0.1346	217.9099

Framework versions

• Transformers 4.38.0.dev0
• Pytorch 2.1.0+cu118
• Datasets 2.17.0
• Tokenizers 0.15.2