trueto

medbert

本项目开源硕士毕业论文“BERT模型在中文临床自然语言处理中的 应用探索与研究”相关模型

transformers_sklearn

A Fitting, Scoring and Predicting Toolkit for Transformer Series Models.

ERNIE2Torch

a script from ERNIE1.0 or ERNIE2.0 to transfomers' BERT format

CCLUE

A benchmark for Chinese ClinicalLanguage Understanding Evalution（CCLUE）

albert_question_match

This code is for paper "ALBERT-QM:An ALBERT Model Based Method for Chinese Health Related Question Matching"

bertology_sklearn

TestIME

TestIME: An Application for Evaluating Chinese Input Method Engines in Electronic Medical Record Entry Task

a_journey_into_math_of_ml

bert-sklearn

a sklearn wrapper for Google's BERT model

CHLUE

A benchmark for Chinese Health Language Understanding Evalution

chnlp_bert

a tookit for explore the capibility of BERT

DDSP-SVC

Real-time end-to-end singing voice conversion system based on DDSP (Differentiable Digital Signal Processing)

DeepFaceLab

DeepFaceLab is the leading software for creating deepfakes.

MedicalChatBox

The data and codes for the baseline setting of medical chatbox.

pdfminer.six

Community maintained fork of pdfminer

Pretrained-Language-Model

Pretrained language model and its related optimization techniques developed by Huawei Noah's Ark Lab.

pytorch-crf

(Linear-chain) Conditional random field in PyTorch.

pytorch-transformers

👾 A library of state-of-the-art pretrained models for Natural Language Processing (NLP)

react-grid-layout

A draggable and resizable grid layout with responsive breakpoints, for React.

react-resizable

A simple React component that is resizable with a handle.

Research

novel deep learning research works with PaddlePaddle

Retrieval-based-Voice-Conversion-WebUI

Voice data <= 10 mins can also be used to train a good VC model!

roop

one-click deepfake (face swap)

SadTalker

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

SadTalker-Video-Lip-Sync

本项目基于SadTalkers实现视频唇形合成的Wav2lip。通过以视频文件方式进行语音驱动生成唇形，设置面部区域可配置的增强方式进行合成唇形（人脸）区域画面增强，提高生成唇形的清晰度。使用DAIN 插帧的DL算法对生成视频进行补帧，补充帧间合成唇形的动作过渡，使合成的唇形更为流畅、真实以及自然。

sd-parseq

THUOCL

THUOCL（THU Open Chinese Lexicon）中文词库

tutorials

virtualenv

Virtual Python Environment builder

vision

Datasets, Transforms and Models specific to Computer Vision