hub

CodeZen

CodeZen

一个专注中文区的 GitHub 项目发现

avatar

Yuxi-Know

结合LightRAG 知识库的知识图谱智能体平台。LangChain v1 + Vue + FastAPI。集成主流大模型、LightRAG、MinerU、PP-Structure、Neo4j 、联网检索、工具调用。

docker fastapi kbqa kgqa llms
star2.3k
Python
avatar

bilive

极快的B站直播录制、自动切片、自动渲染弹幕以及字幕并投稿至B站,综合多种模态模型,兼容超低配置机器。Extremely fast live recording, automatic slicing, rendering, uploading and Integrating MLLMs. Compatible with low configurations machines.

ass bili bilibili bilive danmaku
star3.0k
Python
avatar

Kolors

中文&nbsp | &nbspEnglish&nbsp --> -->             Kolors: Effective Training of Diffusion Model for Photorealistic Text-to-Image Synthesis 目录 - 🎉 新闻新闻 - 📑 开源计划开源计划 - 📖 模型介绍模型介绍 - 📊 评测表现 🥇🥇🔥🔥评测表现 - 🎥 可视化可视化 - 🛠️ 快速使用快速使用

star4.6k
Python
avatar

voice-pro

<!-- title: Voice-Pro: Ultimate AI Voice Conversion and Multilingual Translation Tool description: Powerful AI-powered web application for YouTube video processing, speech recognition, translation, and text-to-speech with multilingual support keywords: AI voice conversion, YouTube trans

audiobook faster-whisper gradio karaoke podcasts
star5.0k
Python
avatar

SenseVoice

SenseVoice 「简体中文」|「English./README.md」|「日本語./README_ja.md」 SenseVoice 是具有音频理解能力的音频基础模型,包括语音识别(ASR)、语种识别(LID)、语音情感识别(SER)和声学事件分类(AEC)或声学事件检测(AED)。本项目提供 SenseVoice 模型的介绍以及在多个任务测试集上的 benchmark,以及体验模型所需的环境安装的与推理方式。 Homepage | 最新动态 | 性能评测 | 环境安装 | 用法教程 | 联系我们 模型仓库:modelscopehttps:/

ai aigc asr audio-event-classification cross-lingual
star6.9k
Python
avatar

SurfSense

EnglishREADME.md | 简体中文README.zh-CN.md SurfSense While tools like NotebookLM and Perplexity are impressive and highly effective for conducting research on any topic/query, SurfSense elevates this capability by integrating with your personal knowledge base. It is a highly customizable AI research

aceternity-ui agent agents ai chrome-extension
star10.4k
Python
avatar

CosyVoice

👉🏻 CosyVoice 👈🏻 **CosyVoice 3.0**: Demoshttps://funaudiollm.github.io/cosyvoice3/; Paperhttps://arxiv.org/abs/2505.17589; CV3-Evalhttps://github.com/FunAudioLLM/CV3-Eval **CosyVoice 2.0**: Demoshttps://funaudiollm.github.io/cosyvoice2/; Paperhttps://arxiv.org/abs/2412.10117; Modelscopehttps://www.

audio-generation cantonese chatbot chatgpt chinese
star17.2k
Python
avatar

BettaFish

微舆:人人可用的多Agent舆情分析助手,打破信息茧房,还原舆情原貌,预测未来走向,辅助决策!从0实现,不依赖任何框架。

agent-framework data-analysis deep-research deep-search llms
star21.9k
Python
avatar

minimind

🚀🚀 「大模型」2小时完全从0训练26M的小参数GPT!🌏 Train a 26M-parameter GPT from scratch in just 2h!

artificial-intelligence large-language-model
star32.7k
Python
avatar

MikroTikPatch

感谢赞助 DartNodeaffhttps://dartnode.com?aff=SnazzyLobster067 | ZMTOaffhttps://console.zmto.com/?affid=1588 | Vultraffhttps://www.vultr.com/?ref=9807160-9J MikroTik RouterOS Patch EnglishREADME_EN.md Discordhttps://discord.gg/keV6MWQFtX Telegramhttps://t.me/mikrotikpatch KeygenTelegram Bothttps:

star1.9k
Python
avatar

Qwen2-Audio

中文&nbsp | &nbspEnglish Qwen2-Audio-7B 🤖 | 🤗&nbsp | Qwen-Audio-7B-Instruct 🤖 | 🤗&nbsp | Demo 🤖 | 🤗&nbsp 📑 Paper &nbsp&nbsp | &nbsp&nbsp 📑 Blog &nbsp&nbsp | &nbsp&nbsp 💬 WeChat 微信&nbsp&nbsp | &nbsp&nbsp Discord&nbsp&nbsp 我们介绍Qwen-Audio的最新进展:Qwen2-Audio。作为一个大规模音频语言模型,Qwen2-Audio能够接受各种

star1.9k
Python
avatar

o-lib

开源图书Olib客户端源代码 由于代码内部有冗余包,因此目前没有提供环境文件requirements.txt,需要手动进行安装。 你可以在BiliBili找到我. 也可以关注我的公众号【拾壹0x7f】。

star2.3k
Python