shrivastava95

bing-chilling

A basic implementation of a Bing Chat webscraper, with image and text uploads!

docparser

A multilingual document parser that processes PDFs. Built using Google's open source Tesseract OCR, and OpenAI's CLIP (Contrastive Language Image Pretraining).

odia-dictionary

A repository for organizing contributions to the creation of an Odia Dictionary dataset for the Dictionary Augmented Translations project in C4GT'23.

sparsernn

Repository for the main course project on a new sequence modelling architecture called SparseRNN, for the DL2023 course, semester VI.

ai-tools

AI Tooling to bootstrap applications fast

palm-2-data-gen

A repository for the data generation files for a paper on Learning How to Compose Negatives with CLIP

shared-vm

blabla shared files with ubuntu and popos and stuff

antAdam

Ant-inspired optimization algorithm for better restarts.

autonomous-systems-pa3

Programming assignment for autonomous systems programming assignment 3 - (Phase II) by Jaisidh Singh, Ishaan Shrivastava.

c4gt-milestones

clip-ocr

A repository for organizing contributions related to finetuning and related approaches using OpenAI's CLIP for the Dictionary Augmented Translations project in C4GT'23.

clip-tests

A repository for tracking changes to the ongoing work by Jaisidh Singh and Ishaan Shrivastava, bridging the modality gap between concepts in CLIP text space..

hubtest

lfstesting

testing git lfs

myobsidian

Obsidian workflow for publishing documentation, blogs, daily learnings, work updates, etc. etc.

obsidian-git-sync

personal-blog

My very own zettelkasten blog, inked inside Obsidian and deployed with Quartz

poc_dict_augment_translate

A repository for the POC for constructing and evaluating translation dictionaries.

poc_ocr

A repository for the POC for parsing translation dicitonaries using OCR. This is a part of the C4GT work under ai-tools/dictionary-augmented-transformers.

principles-of-biological-vision

A repository for the Principles of Biological Vision course of semester 7 at IIT Jodhpur. Work done by Ishaan Shrivastava B20AI013

sdxl_btp

speech-understanding

A respository for coursework of the Speech Understanding course at IIT Jodhpur.

speech-understanding-pa2

A repository containing my (Ishaan Shrivastava B20AI013) submission for the Speech understanding Programming Assignment 2

speech-understanding-pa3

supa3

A repository for the Speech Understanding course assignment 3, by Ishaan Shrivastava B20AI013.

supa3gradio

gradio demo for Speech Understanding Programming Assignment 3, made by Ishaan Shrivastava B20AI013

tokenizer

Tokenizer implementation from scratch. Currently implements BPE based on the original GPT-2 paper.

transformer-impl

Reproducing the paper "Attention is All You Need"

UniSpeech-SU

UniSpeech - Large Scale Self-Supervised Learning for Speech

whisper-web