Pranjalya Tiwari's Projects
Approximate Nearest Neighbors in C++/Python optimized for memory usage and loading/saving to disk
A chat application with a built in toxicity detector to prevent reading them.
A series of study on using various data and tools.
Text-to-Audio/Music Generation
An SDK/Python library for Automatic 1111 to run state-of-the-art diffusion models
Official implementation of "Avocodo: Generative Adversarial Network for Artifact-Free Vocoder" (AAAI2023)
Avocodo: Generative Adversarial Network for Artifact-free Vocoder [WIP]
Open Source Image and Video Restoration Toolbox for Super-resolution, Denoise, Deblurring, etc. Currently, it includes EDSR, RCAN, SRResNet, SRGAN, ESRGAN, EDVR, BasicVSR, SwinIR, ECBSR, etc. Also support StyleGAN2, DFDNet.
Chat app using Vue.js and PouchDB
Cinematic Sound Demixing model and inference serving
Clone image movement using PouchDB and Vue.js
Common resources shared among all task repositories
Competitive Programming questions and their solutions from various sources including LeetCode, Hackerrank, Google Kickstart, Codechef and more platforms.
A serverless Video Chat application built from scratch, using Vue.js, available in Web, Android and iOS.
CoronaWhy Common Research and Data Infrastructure for COVID-19
š¤ Diffusers: State-of-the-art diffusion models for image and audio generation in PyTorch
A simplistic Discord bot in Golang.
Face Recognition software using Python with OpenCV library and Tensorflow.
Models and technique to detect and prevent fake news in Twitter.
PyTorch Implementation of FastSpeech 2 : Fast and High-Quality End-to-End Text to Speech
GPU enabled FFMPEG template for Runpod
CUDA compiled ffmpeg for CUDA enabled GPU-utilizing encoding.
A very simple framework for state-of-the-art Natural Language Processing (NLP)
DL PyTorch library for time series forecasting (originally for flood forecasting)
Drawing flowers with the help of Mathematics and ggplot2 library of R in Jupyter notebook.
Focus on prompting and generating
The Gemini API Python SDK enables developers to use Google's state-of-the-art generative AI models to build AI-powered features and applications.
GIZA++ is a statistical machine translation toolkit that is used to train IBM Models 1-5 and an HMM word alignment model. This package also contains the source for the mkcls tool which generates the word classes necessary for training some of the alignment models.