Paarth Neekhara's starred repositories
llama_index
LlamaIndex is a data framework for your LLM applications
particles.js
A lightweight JavaScript library for creating particles
Wav2Lip-GFPGAN
High quality Lip sync
model-reprogramming
Repository for research works and resources related to model reprogramming <https://arxiv.org/abs/2202.10629>
waveguard_defense
This is the codebase for defense framework described in USENIX '21 paper "WaveGuard: Understanding and Mitigating Audio Adversarial Examples"
sail_align
SailAlign is an open-source software toolkit for robust long speech-text alignment implementing an adaptive, iterative speech recognition and text alignment scheme that allows for the processing of very long (and possibly noisy) audio and is robust to transcription errors. It is mainly written as a perl library but its functionality also depends on freely available software, namely HTK, srilm and sclite.
pytorch-image-models
PyTorch image models, scripts, pretrained weights -- ResNet, ResNeXT, EfficientNet, NFNet, Vision Transformer (ViT), MobileNet-V3/V2, RegNet, DPN, CSPNet, Swin Transformer, MaxViT, CoAtNet, ConvNeXt, and more
Resemblyzer
A python package to analyze and compare voices with deep learning
FaceForensics
Github of the FaceForensics dataset
pocketsphinx.js
Speech recognition in JavaScript and WebAssembly
Tutorial_BayesianCompressionForDL
A tutorial on "Bayesian Compression for Deep Learning" published at NIPS (2017).
deep-image-prior
Image restoration with neural networks but without learning.