makinglong's repositories
Native-LLM-for-Android
Demonstration of running a native LLM on Android device.
Amphion
Amphion (/æmˈfaɪən/) is a toolkit for Audio, Music, and Speech Generation. Its purpose is to support reproducible research and help junior researchers and engineers get started in the field of audio, music, and speech generation research and development.
LLMsPracticalGuide
A curated list of practical guide resources of LLMs (LLMs Tree, Examples, Papers)
EmotionDetection
该项目专注于识别智能对话场景中的用户文本，自动判断情绪类别并给出相应的准确度。可以广泛应用于社交媒体评论情感分析、智能客服情绪分析等场景，成为情感支持工具，帮助用户 从情绪中解脱。多次Prompt提升后，GPT模型最终识别准确率高于人类Baseline水准。
speechmetrics
A wrapper around speech quality metrics MOSNet, BSSEval, STOI, PESQ, SRMR, SISDR
DragGAN
Official Code for DragGAN (SIGGRAPH 2023)
ChatGPT-Next-Web
One-Click to deploy well-designed ChatGPT web UI on Vercel. 一键拥有你自己的 ChatGPT 网页服务。
feishu-chatgpt
🎒飞书 ×（GPT-3.5 + DALL·E + Whisper）= 飞一般的工作体验 🚀 语音对话、角色扮演、多话题讨论、图片创作、文档导出 🚀
chatgpt-mirai-qq-bot
🚀 一键部署！真正的 ChatGPT QQ 聊天机器人！支持ChatGPT API、 ChatGPT Plus、新版 Bing，多账号负载均衡，人设调教，敏感词检测，虚拟女仆、对话上下文，图片渲染，代理加速 (内有视频教程）
sentencepiece
Unsupervised text tokenizer for Neural Network-based text generation.
Hadamard-Matrix-for-hashing
CVPR2020: Central Similarity Quantization/Hashing for Efficient Image and Video Retrieval
faceswap
Deepfakes Software For All
face_classification
Real-time face detection and emotion/gender classification using fer2013/imdb datasets with a keras CNN model and openCV.
face_recognition
The world's simplest facial recognition api for Python and the command line
voca
This codebase demonstrates how to synthesize realistic 3D character animations given an arbitrary speech signal and a static character mesh.
flask-keras-cnn-image-retrieval
🚀CNN-based image retrieval built on Keras
jynew
金庸群侠传3D重制版
kwswitch
智能开关平台，包含服务端、硬件端、安卓端和前端。关键词：物联网开关、远程开关、红外线遥控开关、WIFI继电器、MQTT协议、ESP8266、Iot smart switch、Android、Spring boot、Vue、Arduino
Unity3DTraining
Unity的练习项目
UnityRenderStreaming
Streaming server for Unity
mace
MACE is a deep learning inference framework optimized for mobile heterogeneous computing platforms.
AssetStudio
AssetStudio is a tool for exploring, extracting and exporting assets and assetbundles.
fairseq
Facebook AI Research Sequence-to-Sequence Toolkit written in Python.
WenetSpeech
A 10000+ hours dataset for Chinese speech recognition
TTS-1
🐸💬 - a deep learning toolkit for Text-to-Speech, battle-tested in research and production
MockingBird
🚀AI拟声: 5秒内克隆您的声音并生成任意语音内容 Clone a voice in 5 seconds to generate arbitrary speech in real-time
heti
赫蹏（hètí）是专为中文内容展示设计的排版样式增强。它基于通行的中文排版规范而来，可以为网站的读者带来更好的文章阅读体验。
STT
The deep learning toolkit for Speech-to-Text. Training and deploying STT models has never been so easy.
gameplay
Open-source, cross-platform, C++ game engine for creating 2D/3D games.