README.md

metadata

language: ar
pipeline_tag: automatic-speech-recognition
tags:
  - CTC
  - Attention
  - pytorch
  - Transformer
license: cc-by-nc-4.0
datasets:
  - MGB-3
  - egyptian-arabic-conversational-speech-corpus
metrics:
  - wer
model-index:
  - name: omarxadel/hubert-large-arabic-egyptian
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        metrics:
          - name: Test WER
            type: wer
            value: 29.3755
          - name: Validation WER
            type: wer
            value: 29.1828

Wav2Vec2-XLSR-53 - with CTC fine-tuned on MGB-3 and Egyptian Arabic Conversational Speech Corpus (No LM)

This model is a fine-tuned version of Wav2Vec2-XLSR-53. We finetuned this model on the MGB-3 and Egyptian Arabic Conversational Speech Corpus datasets, acheiving WER of 29.3755%.

The performance of the model on the datasets is the following:

Valid WER	Test WER
29.18	29.37

Acknowledgement

Model fine-tuning and data processing for this work were performed as a part of a Graduation Project from Faculty of Engineering, Alexandria University, CCE Program.