Projects

CareerNavigator
- Developed a Machine Learning model, CareerNavigator, to assess candidates’ employability by analyzing key attributes and predicting suitability for a job role.
- Cleaned, pre-processed, and performed feature engineering on the dataset containing 70k+ datapoints.
- Designed, trained, and evaluated multiple algorithms, utilizing performance metrics such as accuracy, confusion matrix, and F1-score to optimize model effectiveness.
- Selected kernel support vector machine as the best-fit model with the highest accuracy of 80% and F1 score of 0.82.
- Successfully showcased the project to faculty and industry experts, receiving recognition for its innovation and effectiveness.
AudeX: Vision-to-Speech Model
- Developed a dynamic web application combining Optical Character Recognition (OCR) and Text-to-Speech (TTS) technologies to improve accessibility.
- Integrated Tesseract for multi language OCR and Web Speech API for TTS, enabling accurate text extraction from images and high-quality text-to-speech conversion.
- Designed a responsive interface with intuitive navigation, ensuring a seamless user experience.
- Enabled PDF export, word/character count, and keyword search for efficient document handling.
- Developed functionality for managing user profiles, such as signup, login, activity tracking, and editable data.
Advanced Text to Speech Optimization
- Fine-tuned Microsoft's SpeechT5 model to improve pronunciation of Technical English Terms focusing on modifying the phonetic representation to ensure precise pronunciation of abbreviations and acronyms.
- Achieved 25% enhancement in speech quality of over the baseline TTS model, with significant improvements in handling technical terms.
- Optimized the baseline model to generate a Native Italian Voice by enhancing pronunciation, prosody, and stress patterns in line with the phonological rules of the Italian language, significantly improving speech quality and naturalness compared to other existing models.
- Harnessed tools like Transformers, PyTorch, and Hugging Face Datasets to implement advanced machine learning and NLP techniques, ensuring optimal model performance and reliability.
- Implemented dynamic quantization techniques to optimize model efficiency, reducing memory usage and boosting inference speed by up to 30%.
Computer Vision Object Detection System
- Developed an object detection system utilizing YOLOv5 and PyTorch, designed to capture and process individual photos for object detection.
- Optimized the computer vision pipeline to achieve 30+ FPS processing speed for 640x640 input resolution.
- Created a visualization system to render detection results with color-coded bounding boxes and confidence scores ranging from 0 to 1.
- Applied non-maximum suppression with IoU threshold of 0.3 for optimal detection accuracy.
- Added support for 80+ COCO dataset object types, with confidence threshold filtering at 0.3.
Solar Panel Detection System
- Developed an object detection model using YOLOv8n to identify and locate solar panels from aerial imagery.
- Pre-processed and annotated a dataset of satellite images, ensuring high-quality training data for model optimization.
- Trained and fine-tuned the model using PyTorch, achieving high detection accuracy with optimized precision and recall.
- Implemented performance evaluation metrics such as mAP (mean Average Precision) to assess model effectiveness.
- Designed a streamlined pipeline for real-time inference, enhancing efficiency for large-scale image processing.

Aumkesh Chaudhary

About me

Education

Projects

Extracurricular Activities