For employers

Hire this AI Trainer

Sign in or create an account to invite AI Trainers to your job.

Invite to Job
Wala Mandhouj

Wala Mandhouj

Multilingual NLP, GenAI & Computer Vision Labeling Specialist (EN/FR)

Tunisia flagmonastir, Tunisia
$6.00/hrEntry LevelLabel StudioInternal Proprietary Tooling

Key Skills

Software

Label StudioLabel Studio
Internal/Proprietary Tooling

Top Subject Matter

No subject matter listed

Top Data Types

ImageImage
TextText

Top Task Types

Classification
Emotion Recognition
Object Detection
Segmentation
Text Generation

Freelancer Overview

I have solid experience in data labeling and AI training, specializing in computer vision and natural language processing tasks. I have worked extensively on annotating real-time facial emotion datasets using CNN-based models and PyTorch, ensuring high-quality labels for emotion classification systems. Additionally, I am proficient in multilingual NLP data labeling, handling text classification and generative AI datasets in both English and French. My familiarity with popular annotation tools like Label Studio, CVAT, and Doccano allows me to efficiently manage diverse data types including images, video, and text. My technical skills extend to data preprocessing, annotation quality control, and collaborating closely with model training teams to optimize dataset accuracy and consistency. With a strong foundation in aeronautical engineering and data science, I bring analytical rigor and a methodical approach to AI training data projects, contributing to robust and scalable AI solutions.

Entry LevelArabicFrenchEnglish

Labeling Experience

Facial Emotion Recognition System

Internal Proprietary ToolingImageEmotion Recognition
Developed a real-time facial emotion recognition system capable of detecting and classifying human emotions from webcam video input. The system uses a fine-tuned MobileNetV2 model for RGB inputs and a custom CNN for grayscale image inputs (48x48), trained on annotated facial expression datasets. I was responsible for the entire data labeling pipeline, including facial ROI extraction, emotion class labeling, and dataset normalization using tools like Label Studio and OpenCV. Integrated a modular architecture for real-time inference, leveraging multi-file project design to separate concerns (model loading, preprocessing, webcam streaming, and emoji display). Emphasized high-accuracy classification across key emotions such as happy, sad, angry, and surprised. This project showcases my ability to annotate, preprocess, and utilize emotion data effectively for deep learning tasks.

Developed a real-time facial emotion recognition system capable of detecting and classifying human emotions from webcam video input. The system uses a fine-tuned MobileNetV2 model for RGB inputs and a custom CNN for grayscale image inputs (48x48), trained on annotated facial expression datasets. I was responsible for the entire data labeling pipeline, including facial ROI extraction, emotion class labeling, and dataset normalization using tools like Label Studio and OpenCV. Integrated a modular architecture for real-time inference, leveraging multi-file project design to separate concerns (model loading, preprocessing, webcam streaming, and emoji display). Emphasized high-accuracy classification across key emotions such as happy, sad, angry, and surprised. This project showcases my ability to annotate, preprocess, and utilize emotion data effectively for deep learning tasks.

2024 - 2024

Education

N

National Engineering School of Bizerte

National Engineering Degree, Engineering

National Engineering Degree
2019 - 2022
P

Preparatory Institute for Engineering Studies of Monastir

University Diploma in Preparatory Studies in Engineering, Mathematics and Physics

University Diploma in Preparatory Studies in Engineering
2017 - 2019

Work History

No Work History added yet

Wala M. hasn’t added any Work History to their OpenTrain profile yet.