itsANURAG's Projects
The objective of this assignment is to extract textual data articles from the given URL and perform text analysis to compute variables from url
This repository contains a Python script that automates filling out and submitting a web form using Selenium WebDriver and generates form field values using OpenAI's API.
This project leverages a custom-trained YOLOv9 model to detect objects related to room cleanliness. Built with Gradio, it provides an interactive web interface where users can upload images and adjust detection parameters. The app returns images with annotated bounding boxes around detected objects, aiding in room organization tasks.
"Driver Drowsiness Detection System" is a comprehensive repository aimed at enhancing road safety by leveraging cutting-edge technology. Our system employs state-of-the-art computer vision and machine learning techniques to detect signs of driver drowsiness in real-time, thus preventing potential accidents caused by driver fatigue.
In the previous repository about EDA on house price prediction, we only did Exploratory Data Analysis on dataset! In this, ML algortihm(Linear_Reg) is also applied along with that!
An LLM powered ChatCSV Streamlit app so you can chat with your CSV files.
In this, i carried out EDA(exploratory data analysis) on adult_data.csv to extract meaningful insights and followed it by applying LogRegression on it.
Comprehensive EDA on House Price Dataset. This project includes feature engineering, feature selection, and visualizations to uncover insights and prepare data for advanced regression techniques. Data sourced from Kaggle's House Prices competition.
friday2 is a user friendly Streamlit app which acts as a interactive chatbot powered by OPENAI and used gpt-model. With availability of chatgpt already in market, friday provides additional features like "option to use mic rather than write","get the response translated in diff languages" etc
TrienGPT-Streamlit-App is a user-friendly web application powered by OpenAI's GPT-3.5 model, TrienGPT. It simplifies language tasks with two key features: text translation and text-to-speech conversion. Translate text between multiple languages and generate lifelike audio output with customizable accents.
For the practical implementation of this project , i have created an app on Streamlit and uploaded on Streamlit Cloud Cloud
"Welcome to the 'Handwritten Digit Recognition using CNN' project. My goal is to harness the power of Convolutional Neural Networks (CNNs) to accurately identify handwritten digits. With a pre-trained model on the MNIST dataset, you can jump right into digit recognition or fine-tune the model to suit your specific needs."
Develop a Python application to extract key information from invoices using machine learning. The project involves training a model, optimizing it for deployment, and running it on a client desktop. The solution should handle various invoice formats in English, Dutch, and French without hardcoded labels.
This repository contains a lane detection pipeline using OpenCV and a Tkinter-based GUI for video comparison. The tool processes input videos to detect and highlight lane lines, and displays both the original and processed videos side by side. Features include curvature calculation, speed control, and dark mode.A project leveraging futuristic ideas
š EasyOCR Streamlit App: Extract text from images effortlessly using EasyOCR and Streamlit. Upload images in PNG, JPG, or JPEG formats, and let the AI do the rest! Built with Python, PIL, and NumPy, hosted on Hugging Face Spaces. Perfect for quick and accurate OCR needs. Made with ā¤ļø by @itsANURAG. š
This is a RAG_enabled chatbot that can answer questions based on a specific pdf knowledge base
This code is a Python script that uses the Streamlit library to create a simple web application for generating Spotify playlists based on the top songs in the US for specific years or a range of years.
An open-source project that uses cutting-edge NLP models and real-time web search to provide dynamic voice query responses. Features include speech-to-text with Nemo, text generation with Mistral-7B, DuckDuckGo search integration, and text-to-speech with edge-tts, all in a user-friendly Gradio interface.
A Gradio-powered web app that answers questions about YouTube videos using their transcripts. It extracts the video transcript, splits it into chunks, creates embeddings with Google Generative AI, and performs similarity searches. Responses are generated using the Gemini Pro language model.