As a freelancer at UvoCorp, I completed and delivered several diverse computer science projects, covering programming, data science, machine learning, web development, assembly language, etc. My expertise, commitment to quality, and adaptability make me a valuable resource for delivering efficient solutions in this dynamic field.

As a research student in PRLab, I spearheaded the development of a chatbot tailored for a Discrete Mathematics course, gaining acomprehensive skill set and insights into AI-driven education tools.I constructed the chatbot's front-end web application using Python within the Flask framework, supplemented with HTML, CSS, and Bootstrap for user-friendly design and responsiveness.Simultaneously, I conducted research to enhance the chatbot's capabilities, staying updated with the latest AI and educational technology trends.Furthermore, I played a pivotal role in data cleaning and organization, ensuring data accuracy and seamless integration into the chatbot's knowledge base.I have worked on several deep learning projects involving GANs and collaborated on multiple research publications.This dynamic experience equipped me with a well-rounded skill set and deepened my understanding of AI-driven educational tools.

Text to Video Generator:A project focused on generating videos based on text prompts. My roles in this project were mostly related to computer vision such as improving video quality, working with image frames etc as well as speech recognition such as generating sounds based on text input, all using GANs. The project involved usage of Llama model for video generation based on text.PDF text extractor:A Python project focused on extracting text from PDF documents efficiently. This project specializes inextracting text from PDF documents(also old pdf files with half visible text), employing the PyMuPDFlibrary for efficient text extraction . This tool automates and simplifies the process of working withextensive text content embedded within PDF files. It serves as a valuable resource for various taskssuch as data analysis, information retrieval, and content processing. The PyMuPDF library enhances theproject's capabilities, ensuring accurate and reliable text extraction from a wide range of PDF documents.TTS and STT (Speech recognition):I completed projects involving speech recognition systems. Developed speech-to-text and text-to-speech generating systems using pretrained models, specifically GAN models.

I immersed myself in web application development using Blazor, collaborating closely with a proficientteam. Together, we crafted interactive and responsive user interfaces, leveraging .NET within Blazor'scomponent-based structure. This experience not only honed my technical skills but also underscored thesignificance of teamwork and adhering to best practices in software development.In addition to web development, I seized the opportunity to work on speech-to-text recognition,further expanding my skill set and deepening my passion for technology. This internship was trulytransformative, equipping me with a well-rounded set of skills and a heightened enthusiasm for impactfulweb solutions.Furthermore, I employed the MVC (Model-View-Controller) architecture to structure and organize the webapplication. This approach facilitated the separation of concerns and improved maintainability, makingit easier to develop, test, and manage the application components effectively.