Starred repositories
🧸 Lobe Vidol - Making Virtual Idols Accessible for EveryOne
🌐 The Internet OS! Free, Open-Source, and Self-Hostable.
Official code for "F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matching"
Multi-lingual large voice generation model, providing inference, training and deployment full-stack ability.
绝区零 一条龙 | 全自动 | 自动闪避 | 自动每日 | 自动空洞 | 支持手柄
实时语音交互数字人,支持端到端语音方案(GLM-4-Voice - THG)和级联方案(ASR-LLM-TTS-THG)。可自定义形象与音色,无须训练,支持音色克隆,首包延迟低至3s。Real-time voice interactive digital human, supporting end-to-end voice solutions (GLM-4-Voice - THG) and …
🎬 卡卡字幕助手 | VideoCaptioner - 基于 LLM 的智能字幕助手,无需GPU一键高质量字幕视频合成!支持生成、断句、优化、翻译全流程。让视频字幕制作简单高效!
A live2D chatbot Demo build with python and js.
Web AR sample application combining Live2D Cubism SDK and AR.js
🧑🚀 全世界最好的LLM资料总结 | Summary of the world's best LLM resources.
SmartSystemMenu extends system menu of all windows in the system
H1DDENADM1N / api4sensevoice
Forked from 0x5446/api4sensevoiceAPI and websocket server for sensevoice. It has inherited some enhanced features, such as VAD detection, real-time streaming recognition, and speaker verification.
离线语音输入简/繁体、中译英、字幕转录;在线多译多、云剪贴板等等 (基于SenseVoice模型 支持中粤英日韩多语种)
Multilingual Voice Understanding Model
Pseudo Streaming SenseVoice with Hotwords
API and websocket server for sensevoice. It has inherited some enhanced features, such as VAD detection, real-time streaming recognition, and speaker verification.
Various AI scripts. Mostly Stable Diffusion stuff.
绝区零 | ZenlessZoneZero | 零号空洞 | 自动战斗 | 自动化 | 图片分类 | OCR识别
Understand Human Behavior to Align True Needs
Utilizing GPT to assist interviewees, help answer questions and write code
Ecoute is a live transcription tool that provides real-time transcripts for both the user's microphone input (You) and the user's speakers output (Speaker) in a textbox. It also generates a suggest…