Skip to content
View SoundaryaDube's full-sized avatar

Block or report SoundaryaDube

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don't include any personal information such as legal names or email addresses. Markdown supported. This note will be visible to only you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
SoundaryaDube/README.md

Hi there, I'm Soundarya Dube!

Computer Science student at VIT Bhopal interested in building scalable AI systems.

My work spans machine learning, multimodal AI, and data pipelines. I enjoy working on problems where large models interact with real-world data and interfaces.

Recent work includes:

  • Asynchronous Python pipelines for large-scale web data collection
  • LLM-based structured data extraction using Gemini
  • Evaluation frameworks for Vision-Language Models
  • Spatial consensus systems for UI element detection

Technologies I often use: Python • PyTorch • TensorFlow • OpenCV • FastAPI • Pandas • Asyncio

Currently exploring: LLM systems, multimodal models, and AI automation.

Pinned Loading

  1. surgical-segmentation-app surgical-segmentation-app Public

    Developed an AI-driven diagnostic tool that processes MRI/CT scans using convolutional neural networks (CNNs) to detect tumors and abnormalities with high accuracy.

    Python

  2. ECG-Based_Health_Risk_Stratification_Platform ECG-Based_Health_Risk_Stratification_Platform Public

    Engineered a complex data unification pipeline to integrate six public ECG datasets (MIT-BIH, PTB-XL, SCDH), resolving heterogeneities in lead configurations, sampling rates, and labeling schemas t…

    Jupyter Notebook

  3. Healthcare_presciption_decoding Healthcare_presciption_decoding Public

    The objective is to build a model that takes a 45-60 second spoken audio file (.wav) as input and outputs a continuous grammar score from 0 to 5.

    Jupyter Notebook

  4. breat_cancer_classifier breat_cancer_classifier Public

    This project is a full-stack web application that uses a machine learning ensemble model to classify breast tumors as benign or malignant based on 30 diagnostic features. The frontend is built with…

    TypeScript