whn09

table_structure_recognition

Table detection (TD) and table structure recognition (TSR) using Yolov5/Yolov8, and you can get the same (even better) result compared with Table Transformer (TATR) with smaller models.

VITA

✨✨VITA: Towards Open-Source Interactive Omni Multimodal LLM

wav2lip_288x288

Wav2Lip

This repository contains the codes of "A Lip Sync Expert Is All You Need for Speech to Lip Generation In the Wild", published at ACM Multimedia 2020.

act

ai-models

CodeFormer

[NeurIPS 2022] Towards Robust Blind Face Restoration with Codebook Lookup Transformer

darknet

Convolutional Neural Networks

DeepSeek-R1

Easy-Wav2Lip

Colab for making Wav2Lip high quality and easy to use

EPLB

Expert Parallelism Load Balancer

facefusion

Next generation face swapper and enhancer

flash-attention

Fast and memory-efficient exact attention

FlashMLA

FlashMLA: Efficient MLA decoding kernels

GPT-SoVITS

1 min voice data can also be used to train a good TTS model! (few shot voice cloning)

graphcast

host-yolov8-on-sagemaker-endpoint

InstantID

InstantID : Zero-shot Identity-Preserving Generation in Seconds 🔥

iTransformer

Official implementation for "iTransformer: Inverted Transformers Are Effective for Time Series Forecasting".

langchain

⚡ Building applications with LLMs through composability ⚡

MiniCPM-o

MiniCPM-Llama3-V 2.5: A GPT-4V Level Multimodal LLM on Your Phone

OpenCastKit

The open-source solutions of FourCastNet and GraphCast

pangu-pytorch

Weather forecast at 1/3/6/24-hour horizon

SadTalker

[CVPR 2023] SadTalker：Learning Realistic 3D Motion Coefficients for Stylized Audio-Driven Single Image Talking Face Animation

short_drama_translation

table-transformer

Model training and evaluation code for our dataset PubTables-1M, developed to support the task of table extraction from unstructured documents.

torchrec

Pytorch domain library for recommendation systems

TriplaneGaussian

TriplaneGaussian: A new hybrid representation for single-view 3D reconstruction.

whisper.cpp

Port of OpenAI's Whisper model in C/C++

YOLO-World

[CVPR 2024] Real-Time Open-Vocabulary Object Detection