Instructions to use farahabdou/whisper-small-arabic-transciption with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use farahabdou/whisper-small-arabic-transciption with Transformers:
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("farahabdou/whisper-small-arabic-transciption", dtype="auto") - Notebooks
- Google Colab
- Kaggle
whisper-small-arabic-transciption
This model is a fine-tuned version of openai/whisper-small on farahabdou/FLEURS-AR-EN-split dataset.
Training results
Base Model:
- BLEU: 9.80
- CHRF: 29.17
Fine-tuned Model:
- BLEU: 10.46
- CHRF: 42.97
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support