django9
Follow
Stars
English pronunciation correction teacher built with gemini
A high-quality tool for convert PDF to Markdown and JSON.一站式开源高质量数据提取工具，将PDF转换成Markdown和JSON格式。
real time face swap and one-click video deepfake with only a single image
The fastest digital human algorithm, now on your desktop.
first base model for full-duplex conversational audio
A simple screen parsing tool towards pure vision based GUI agent
The reinforcement learning training code for AgiBot X1.
A chrome extension to easily do visual trials of clothing from any e-commerce store. Here is the easy to use install option 👇
A Lightweight Face Recognition and Facial Attribute Analysis (Age, Gender, Emotion and Race) Library for Python
Netflix-level subtitle cutting, translation, alignment, and even dubbing - one-click fully automated AI video subtitle team | Netflix级字幕切割、翻译、对齐、甚至加上配音，一键全自动视频搬运AI字幕组
An elegent pytorch implement of transformers
An Open-source Neural Hierarchical Multi-label Text Classification Toolkit
The Pytorch implementation of sound classification supports EcapaTdnn, PANNS, TDNN, Res2Net, ResNetSE and other models, as well as a variety of preprocessing methods.
基于大模型搭建的聊天机器人，同时支持 微信公众号、企业微信应用、飞书、钉钉 等接入，可选择GPT3.5/GPT-4o/GPT-o1/ DeepSeek/Claude/文心一言/讯飞星火/通义千问/ Gemini/GLM-4/Claude/Kimi/LinkAI，能处理文本、语音和图片，访问操作系统和互联网，支持基于自有知识库进行定制企业智能客服。
用于从头预训练+SFT一个小参数量的中文LLaMa2的仓库；24G单卡即可运行得到一个具备简单中文问答能力的chat-llama2.
use cnn recognize captcha by tensorflow. 本项目针对字符型图片验证码，使用tensorflow实现卷积神经网络，进行验证码识别。
基于PyTorch&YOLOv4实现的口罩佩戴检测 ⭐ 自建口罩数据集分享
📈📈📈【口罩佩戴检测数据训练 | 开源口罩检测数据集和预训练模型】Train D/CIoU_YOLO_V3 by darknet for object detection
目前，主流蒸馏模型采用方法为KD蒸馏、LD蒸馏或feature蒸馏，然蒸馏开源项目也较少。为此，我写了一份基于yolov5框架的蒸馏，并会有实验附带。该方法将会不断尝试论文方法，不断探索更有效的蒸馏方法。
Twitter US Airline数据集情感分析（sentiment Analysis），使用Bert Sentence encoding作为特征，实现了SVM、XGBoost、RandomForest（随机森林）若干分类器。
A web UI Project In order to learn the large language model. This project includes features such as chat, quantization, fine-tuning, prompt engineering templates, and multimodality.
Skywork series models are pre-trained on 3.2TB of high-quality multilingual (mainly Chinese and English) and code data. We have open-sourced the model, training data, evaluation data, evaluation me…
Chinese Stable Diffusion, zh SD,中文文生图，中文SD，中文Stable Diffusion