Hi there! I'm Saurabh Kumar, a Computer Science Engineering student passionate about Artificial Intelligence, Machine Learning, and Natural Language Processing (NLP). I love solving complex problems, building innovative projects, and contributing to the tech community.

🔭 Currently, I'm working on:

• Fine-tuning state-of-the-art AI models for real-world applications.
• Developing creative solutions in NLP and Generative AI.

🌱 I’m constantly learning:

• Advanced topics in AI, including Reinforcement Learning and Explainable AI.
• Optimization techniques for deploying machine learning models.

• Languages:
• Data Science:
• Tools:
• Cloud:
• Dev Tools:

Description: Developed an advanced Vehicle Classification Model using computer vision and machine learning techniques, leveraging frameworks like TensorFlow and OpenCV. The model employs Convolutional Neural Networks (CNNs) for efficient feature extraction and classification, enabling accurate identification of various vehicle types, such as cars, trucks, and motorcycles, in real-time scenarios. Trained on a diverse dataset, the model achieves high precision, making it suitable for applications in traffic management, autonomous driving systems, and smart surveillance. Its robust performance and scalability highlight expertise in deep learning, image processing, and practical AI deployment for real-world challenges. Technologies: Python, PyTorch, OpenCV

Description: Developed a Fine-Tuned Text-to-Speech (TTS) Model tailored for English technical vocabulary and the regional language Hindi, leveraging the SpeechT5 framework by Hugging Face. The project focuses on synthesizing speech with accurate pronunciation, natural intonation, and contextual understanding of technical jargon and regional nuances. Through dataset creation, preprocessing, and model optimization, the training pipeline ensured high-quality audio outputs while maintaining computational efficiency. Deployed successfully on Hugging Face, the model demonstrates scalability and accessibility, catering to diverse applications in technical education, assistive technology, and language preservation. This work reflects expertise in NLP, speech synthesis, and real-world AI deployment.
Technologies: PyTorch, Hugging Face, NLP

Description: Developed solutions for face detection, pose estimation, and hand tracking using OpenCV.
Technologies: OpenCV, MediaPipe

• Artificial Intelligence and Generative AI
• Conversational AI and Natural Language Processing
• Computer Vision and Advanced Image Processing
• Research and Development in AI-driven solutions

• Completed OpenCV Bootcamp with multiple projects in Computer Vision.
• Applied cutting-edge AI models to solve real-world challenges in NLP and Vision.
• Consistently pushing the boundaries of innovation in AI and ML.

Feel free to explore my repositories and connect with me for collaborations or discussions!