MOSS-TTSD is a spoken dialogue generation model that enables expressive dialogue speech synthesis in both Chinese and English, supporting zero-shot multi-speaker voice cloning, and long-form speech…

自己用的 Autohotkey 脚本，就是把多个脚本变成了一个，方便自己使用。

打灰机守护程序-利用开源AI视觉模型（smolVLM2）与 MediaPipe 库，在你打灰机时保驾护航

Chinese text normalization for speech processing

Added vLLM support to IndexTTS for faster inference.

一个超低延迟的基于GPT-SoVITS语音合成的语音交互系统

An Industrial-Level Controllable and Efficient Zero-Shot Text-To-Speech System

Implements harmful/harmless refusal removal using pure HF Transformers

一个Windows端的屏幕识别工具

Official code for Dynamic Parametric RAG.

By invoking local large language models, this tool processes spreadsheets similar to multi-dimensional tables. It can batch-generate content for Excel/CSV data using AI. The tool supports simultane…

LLM + MCP + RAG = Magic

Godot tutorial collection of my YouTube videos

帮助视觉障碍者识别物品，障碍物提醒

安卓系统定制：从入门到实践 开源图书🔥

AingDesk是一款简单好用的AI助手，支持知识库、模型API、分享、联网搜索、智能体，它还在飞快成长中。 AingDesk is a simple and easy-to-use AI assistant that supports knowledge bases, model APIs, sharing, internet search, and intelligent agents.…

🚀 The fast, Pythonic way to build MCP servers and clients

本项目为xiaozhi-esp32提供后端服务，帮助您快速搭建ESP32设备控制服务器。Backend service for xiaozhi-esp32, helps you quickly build an ESP32 device control server.

LLMs-from-scratch项目中文翻译

An Industrial-Level Controllable and Efficient Zero-Shot Text-To-Speech System

持续更新，欢迎star，保姆级改装教程：

SoftWhisper simplifies audio and video transcription using the powerful Whisper model. Easily select custom models, languages, and tasks, fine-tune transcription with beam size adjustment, and spec…

Algorithm for 3D printer with new kinematics

SpatialLM: Training Large Language Models for Structured Indoor Modeling

[ICLR 2024] Efficient Streaming Language Models with Attention Sinks

recombination of audio_contasnet