README.md

metadata

language:
  - ar
license: apache-2.0
base_model: openai/whisper-medium
tags:
  - hf-asr-leaderboard
  - generated_from_trainer
datasets:
  - google/fleurs
metrics:
  - wer
model-index:
  - name: Whisper Small ar -team 1
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: fleurs data
          type: google/fleurs
          config: ar_eg
          split: None
          args: 'config: ar_eg, split: test'
        metrics:
          - name: Wer
            type: wer
            value: 45.28601694915254

Whisper Small ar -team 1

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

• Loss: 0.9206
• Wer: 45.2860

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: 5e-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

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.0001	76.92	1000	0.9206	45.2860

Framework versions

• Transformers 4.39.0.dev0
• Pytorch 2.1.2+cu121
• Datasets 2.18.0
• Tokenizers 0.15.2