This Tunisian Automatic Speech Recognition (ASR) project focuses on developing a system that can accurately transcribe spoken Tunisian Arabic into text. It's a finetuned on a WavLM (an extension of Wav2Vec 2.0 which uses a transformer architecture ) as a base Model and boosted with a KenLM language model located in language_model/languageModel.arpa.

Tested On a Private Dataset

Make sure that you installed the huggingface client before cloning the repo .

Check the hyper parameters file hyperparams.yaml and verify the path of the language model.

To run the web app you have only to execute:

If you have questions, you can send an email to : benrejebdhaker3@gmail.com