shuiniu86's repositories
Cognitive-Speech-TTS
Microsoft Text-to-Speech API sample code in several languages, part of Cognitive Services.
2018AICity_TeamUW
The winning method in Track 1 and Track 3 at the 2nd AI City Challenge Workshop in CVPR 2018 - Official Implementation
Audio2Face-1
http://www.facegood.cc
Awesome-Chinese-LLM
整理开源的中文大语言模型，以规模较小、可私有化部署、训练成本较低的模型为主，包括底座模型，垂直领域微调及应用，数据集与教程等。
bert_seq2seq
pytorch实现 Bert 做seq2seq任务，使用unilm方案,现在也可以做自动摘要，文本分类，情感分析，NER，词性标注等任务,支持t5模型，支持GPT2进行文章续写。
BlogLearning
自己的学习历程，重点包括各种好玩的图像处理算法、运动捕捉、机器学习
ChatGPT-Feishu
给飞书准备的 ChatGPT 机器人
cognitive-services-speech-sdk
Sample code for the Microsoft Cognitive Services Speech SDK
CPP
Lecture notes, projects and other materials for Course 'CS205 C/C++ Program Design' at Southern University of Science and Technology.
DECA
DECA: Detailed Expression Capture and Animation (SIGGRAPH 2021)
deep-learning-for-image-processing
deep learning for image processing including classification and object-detection etc.
deformxfer
A C++ header-only implementation of "Deformation Transfer for Triangle Meshes"
iFlytek-Flask-OCR-TTS
The project is a demo for OCR and TTS, which use the iFlytek API, running in Flask
kalidokit
Blendshape and kinematics solver for Mediapipe/Tensorflow.js face, eyes, pose, and hand tracking models.
lazydocker
The lazier way to manage everything docker
metahuman-stream
Real time streaming digital human based on nerf
metahuman_rig_transfer
A series of python scripts to modify the metahuman rig into a new one for Maya.
mocap4face
A free, multiplatform SDK for real-time facial motion capture using blendshapes, and rigid head pose in 3D space from any RGB camera, photo, or video.
PaddlePaddle-DeepSpeech
基于PaddlePaddle实现的语音识别，中文语音识别。项目完善，识别效果好。支持Windows，Linux下训练和预测，支持Nvidia Jetson开发板预测。
Puppeteer
A UE5 plugin for improving the Metahuman ARKit face tracking.
RingNet
Learning to Regress 3D Face Shape and Expression from an Image without 3D Supervision
strongtrack
A python tool with facial landmark annotation and coefficient finder
TensorflowASR
集成了Tensorflow 2版本的端到端语音识别模型，并且RTF(实时率)在0.1左右/Mandarin State-of-the-art Automatic Speech Recognition in Tensorflow 2
tortoise-tts
A multi-voice TTS system trained with an emphasis on quality
util_tool
记录我一些关于三维模型常用的工具代码，会不断更新