Skip to content
View SRDdev's full-sized avatar
:octocat:
Empowering lives through AI
:octocat:
Empowering lives through AI

Highlights

  • Pro
Block or Report

Block or report SRDdev

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.

Please don't include any personal information such as legal names or email addresses. Maximum 100 characters, 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
SRDdev/README.md

Hey! I am Shreyas Dixit

President @MLSC VIIT Pune | Student Researcher | Dual Patent Holder | Deep Learning

srddev

shreyas__dixit i

🧑🏻About Me

  • 🔭 I am into Deep Learning Architectures and Techniques
  • 🤗 Publishing ML Models on Huggingface
  • 👨‍💻 All of my projects are available at shreyasdixit.me
  • 🧋 Motto Lead Learn Inspire

Latest Updates

  • 2nd Patent Published :Second Patent in 2023 "Real-Time MultiModal Video Narration Platform for Visually Impaired People"
  • Indian Patent Published : Recently published an Indian Patent titled "Assistance Platform for Visually Impaired Person using Image Captioning"

Projects

Click on the project name to directly go to it's GitHub Repository and click demo app to see a live demo of the project

  • EchoSense : VisualAudioAI is a multimodality model that aims to generates Audio descriptions by looking at any given Image.[HF Space]
  • HingFlow : Translation model to translate English sentence to Hindi. Used Neural Machine Translation using Transformers approach to solve this problem.[HF Space]
  • MaskedLM : A Pytorch Implementation of BART Architecure for Masked Language Modeling on English & Hinglish Data.The Models are available to use on Huggingface. [HF Model card]
  • Neural Translation : A transformer based Neural Machine Translation model in TensorFlow for English to Hinglish Translation.Built from scratch & achived 94% accuracy with 24hr for Neuro Hackathon.
  • Image Captioning : Multimodality model for Image-Text Generation. Given any image the model outputs a text prompt describing the image.

Currently working on

  • Open Source contributions

Notion & NewsLetter

  • I write about productivity in this weekly newsletter "Productivity Pro".
  • I use Notion daily as my second brain. I also create Notion templates for you to stay organized and Productive.

  • I have multiple Notion Templates on Notion's Official Gallery

Pinned

  1. YouTube-Llama YouTube-Llama Public

    A question-answering chatbot for any YouTube video using Local Llama2 & Retrival Augmented Generation

    Python 3 2

  2. ScriptForge ScriptForge Public

    ScriptGPT is a model series which allows users to generate YouTube , Video scripts. These scripts can be used to create new and exciting content.

    Jupyter Notebook 5

  3. Neurohack Neurohack Public

    This project uses a transformer-based neural network to translate English to Hinglish, a colloquial form of Hindi that incorporates English words and phrases. The model is built from scratch using …

    Jupyter Notebook 3 1

  4. Model-Quantization Model-Quantization Public template

    Quantization is a technique to reduce the computational and memory costs of running inference by representing the weights and activations with low-precision data types like 8-bit integer (int8) ins…

    Jupyter Notebook 3

  5. Aerial-Segmentation-Models Aerial-Segmentation-Models Public

    A repository of aerial image semantic segmentation contains annotated images that have been labeled with object categories, enabling machine learning models to identify and classify objects in aeri…

    Jupyter Notebook

  6. Image-Generation Image-Generation Public

    Welcome to the "Image Generation from Scratch" repository! This project is dedicated to building image generation models from scratch using PyTorch. In this repository, you'll find both GANs (Gener…

    Python 1