Skip to content
View inboxpraveen's full-sized avatar
🎯
Focusing
🎯
Focusing
46 followers · 1 following

Achievements

Achievement: YOLOAchievement: Pull SharkAchievement: StarstruckAchievement: Arctic Code Vault Contributor

Achievements

Achievement: YOLOAchievement: Pull SharkAchievement: StarstruckAchievement: Arctic Code Vault Contributor
Block or Report

Block or report inboxpraveen

Report abuse

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

Report abuse
inboxpraveen/README.md

Hello, world! 👋 I'm Praveen Kumar (PK)

🛠 Senior AI Architect | 🎤 Educator | ✍️ Tech Blogger

I'm based in the heart of innovation, Silicon Valley of India - Bengaluru. Building scalable AI products, diving deep into natural language processing, speech recognition, and computer vision, and sharing my knowledge with the world is what I live for. Let's make the tech community stronger, together!

🆕 What's New I am working on?

I am recently working on LLM powered local hosted applications such as chatbots, PDF Parsers, Search engines, and Lang Chain. 🐦

🌐 Connect with me:

🚀 What I Do:

  • 🔍 Natural Language Processing: Unlocking the power of text.
  • 🗣 Speech Recognition: Making machines understand us better.
  • 👁 Computer Vision: Giving sight to computers.
  • 🐍 Python Enthusiast: Writing efficient and optimized production codes.

🛠 Recent Projects:

  1. Context Vector Search Engine - A simple 🖥️ interface where users can search 🔍 for contextually relevant text passages in documents. It employs BERT model for semantic embeddings and FAISS for efficient similarity search. When users enter a query, the system returns the most contextually relevant text passage from the corpus and highlights the matched keywords.🚀 🔗 Repository

  2. Speech Recognition & Correction Tool - 🎙️📝 A powerful Flask-based web application that leverages the latest Hugging Face ASR models to provide real-time speech-to-text (STT) transcripts with an intuitive user interface for easy correction. Perfect for enhancing the quality of training datasets for ASR models. 🚀. 🔗 Repository

  3. Minutes of Meeting - .🎤📄 An innovative tool that transforms audio or video files into text transcripts and generates concise meeting minutes. Stay organized and efficient in your meetings, and get ready for Phase 2 where we'll be open for contributions to enable real-time meeting transcription! 🚀🔗 Repository

  4. ... Check more here

📊 This week's stats:

PK's GitHub Stats

⭐ Remember, the world is better when we share knowledge. Let's connect and inspire others!

Pinned Loading

  1. FIFA-18-Management-System FIFA-18-Management-System Public

    This repository contains the whole project. This project was intended to exhibit as a DBMS project but it can also act as a web development project as it includes complete front end and back end.

    JavaScript 62 28

  2. movie-recommendation-system movie-recommendation-system Public

    Movie Recommendation System with Complete End-to-End Pipeline, Model Intregration & Web Application Hosted. It will also help you build similar projects.

    Jupyter Notebook 87 42

  3. Autoencoders-and-decoders-using-keras-and-tensorflow Autoencoders-and-decoders-using-keras-and-tensorflow Public

    This repo contains auto encoders and decoders using keras and tensor flow. It shows the exact encoding and decoding with the code part.

    Jupyter Notebook 18 9

  4. inboxpraveen.github.io inboxpraveen.github.io Public

    My portfolio website to showcase my skills, projects, and technical blogs.

    CSS 6 2

  5. context-search-engine context-search-engine Public

    A simple interface where users can search for contextually relevant text passages in documents. It employs DistilBERT model for semantic embeddings and FAISS for efficient similarity search. When u…

    Python 8 2

  6. ASR-Accuracy-Tool ASR-Accuracy-Tool Public

    🎙️📝 A powerful Flask-based web application that leverages the latest Hugging Face ASR models to provide real-time speech-to-text (STT) transcripts with an intuitive user interface for easy correcti…

    Python 4 4