README.md

metadata

base_model: openai/whisper-large-v3
datasets:
  - MightyStudent/Egyptian-ASR-MGB-3
language:
  - ar
library_name: peft
license: apache-2.0
metrics:
  - wer
tags:
  - generated_from_trainer
model-index:
  - name: Whisper large V3 Arabic
    results:
      - task:
          type: automatic-speech-recognition
          name: Automatic Speech Recognition
        dataset:
          name: MightyStudent/Egyptian-ASR-MGB-3
          type: MightyStudent/Egyptian-ASR-MGB-3
        metrics:
          - type: wer
            value: 38.095238095238095
            name: Wer

Whisper large V3 Arabic

This model is a fine-tuned version of openai/whisper-large-v3 on the MightyStudent/Egyptian-ASR-MGB-3 dataset. It achieves the following results on the evaluation set:

• Loss: 0.6890
• Wer: 38.0952

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: 2
• eval_batch_size: 2
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 5
• num_epochs: 1
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.6852	0.2	10	0.7062	45.7143
0.7504	0.4	20	0.6994	45.7143
0.7219	0.6	30	0.6940	45.7143
0.6971	0.8	40	0.6905	45.7143
0.6846	1.0	50	0.6890	38.0952

Framework versions

• PEFT 0.12.0
• Transformers 4.44.2
• Pytorch 2.4.0+cu121
• Datasets 3.0.0
• Tokenizers 0.19.1