Repositories list

• AI_NovelGenerator

  Public
  使用ai生成多章节的长篇小说，自动衔接上下文、伏笔

  Python

  •

  GNU Affero General Public License v3.0

  •145•0•0•0•Updated Feb 16, 2025Feb 16, 2025

• ktransformers

  Public
  A Flexible Framework for Experiencing Cutting-edge LLM Inference Optimizations

  Python

  •

  Apache License 2.0

  •699•0•0•0•Updated Feb 12, 2025Feb 12, 2025

• esp-sr

  Public
  Speech recognition

  C

  •

  Other

  •115•0•0•0•Updated Feb 12, 2025Feb 12, 2025

• goku

  Public
  Video Generation Foundation Models: https://saiyan-world.github.io/goku/

  Python

  •234•0•0•0•Updated Feb 11, 2025Feb 11, 2025

• rag-web-ui

  Public
  RAG Web UI is an intelligent dialogue system based on RAG (Retrieval-Augmented Generation) technology.

  TypeScript

  •

  Apache License 2.0

  •170•0•0•0•Updated Feb 11, 2025Feb 11, 2025

• InspireMusic

  Public
  InspireMusic: A Unified Framework for Music, Song, Audio Generation.

  Python

  •

  Apache License 2.0

  •71•0•0•0•Updated Feb 10, 2025Feb 10, 2025

• cursor-tools

  Public
  Give Cursor Agent an AI Team and Advanced Skills

  TypeScript

  •

  MIT License

  •108•0•0•0•Updated Feb 10, 2025Feb 10, 2025

• Sonic

  Public
  Official implementation of "Sonic: Shifting Focus to Global Audio Perception in Portrait Animation"

  Python

  •

  Other

  •143•0•0•0•Updated Feb 10, 2025Feb 10, 2025

• FireRedASR

  Public
  FireRedASR is a family of open-source industrial-grade ASR models supporting Mandarin, Chinese dialects and English, achieving a new SOTA on public Mandarin ASR benchmarks, while also offering outstanding singing lyrics recognition capability.

  Python

  •

  Apache License 2.0

  •37•0•0•0•Updated Feb 5, 2025Feb 5, 2025

• 1Prompt1Story

  Public
  (ICLR 2025) One-Prompt-One-Story: Free-Lunch Consistent Text-to-Image Generation Using a Single Prompt

  Python

  •

  MIT License

  •19•0•0•0•Updated Feb 5, 2025Feb 5, 2025

• OpenDeepResearcher

  Public
  Jupyter Notebook

  •

  MIT License

  •299•0•0•0•Updated Feb 3, 2025Feb 3, 2025

• R1-V

  Public
  Witness the aha moment of VLM with less than $3.

  Python

  •212•0•0•0•Updated Feb 3, 2025Feb 3, 2025

• ai-gradio

  Public
  A Python package that makes it easy for developers to create AI apps powered by various AI providers.

  Python

  •169•0•0•0•Updated Feb 1, 2025Feb 1, 2025

• MILS

  Public
  Code release for "LLMs can see and hear without any training"

  Python

  •

  Other

  •16•0•0•0•Updated Jan 31, 2025Jan 31, 2025

• RAGEN

  Public
  RAGEN is the first open-source reproduction of DeepSeek-R1 for training agentic models via reinforcement learning.

  Python

  •

  Apache License 2.0

  •64•0•0•0•Updated Jan 30, 2025Jan 30, 2025

• YuE

  Public
  YuE: Open Full-song Music Generation Foundation Model, something similar to Suno.ai but open

  Python

  •425•0•0•0•Updated Jan 30, 2025Jan 30, 2025

• openai-realtime-solar-system

  Public
  Demo showing how to use the OpenAI Realtime API to navigate a 3D scene via tool calling

  TypeScript

  •

  MIT License

  •48•0•0•0•Updated Jan 29, 2025Jan 29, 2025

• ComfyUI-DeepSeek-JanusPro

  Public
  Python

  •

  GNU General Public License v3.0

  •8•0•0•0•Updated Jan 29, 2025Jan 29, 2025

• PengChengStarling

  Public
  PengChengStarling is specifically designed for developing multilingual ASR models based on the icefall project, supporting a complete ASR pipeline that includes data processing, model training, inference, fine-tuning, and deployment.

  Python

  •14•0•0•0•Updated Jan 27, 2025Jan 27, 2025

• DeepSeek-R1

  Public
  MIT License

  •10k•0•0•0•Updated Jan 26, 2025Jan 26, 2025

• bailing

  Public
  百聆 是一个类似GPT-4o的语音对话机器人，通过ASR+LLM+TTS实现，时延低至800ms，低配置也可运行，支持打断

  Python

  •

  MIT License

  •107•0•0•0•Updated Jan 19, 2025Jan 19, 2025

• kokoro-onnx

  Public
  TTS with kokoro and onnx runtime

  Python

  •

  MIT License

  •150•0•0•0•Updated Jan 15, 2025Jan 15, 2025

• WrenAI

  Public
  🤖 Open-source AI Agent that empowers data-driven teams to chat with their data to generate Text-to-SQL, charts, spreadsheets, reports, and BI. 📈📊📋🧑‍💻

  TypeScript

  •

  GNU Affero General Public License v3.0

  •558•0•0•0•Updated Jan 10, 2025Jan 10, 2025

• openai-realtime-api-nextjs

  Public
  Leverage the OpenAI Realtime API (12-17-2024) with this Next.js 15 starter template featuring shadcn/ui components, tool-calling & localization. Use starter to build Voice AI apps with WebRTC.

  TypeScript

  •

  MIT License

  •47•0•0•0•Updated Jan 10, 2025Jan 10, 2025

• xiaozhi-esp32

  Public
  Build your own AI friend

  C

  •

  MIT License

  •996•0•0•0•Updated Jan 6, 2025Jan 6, 2025

• VITA

  Public
  ✨✨VITA-1.5: Towards GPT-4o Level Real-Time Vision and Speech Interaction

  Python

  •

  Other

  •158•0•0•0•Updated Jan 6, 2025Jan 6, 2025

• speech_recognition

  Public
  Speech recognition module for Python, supporting several engines and APIs, online and offline.

  Python

  •

  BSD 3-Clause "New" or "Revised" License

  •2.4k•0•0•0•Updated Jan 4, 2025Jan 4, 2025

• awesome-llm-apps

  Public
  Collection of awesome LLM apps with RAG using OpenAI, Anthropic, Gemini and opensource models.

  Python

  •

  Apache License 2.0

  •1.9k•0•0•0•Updated Jan 3, 2025Jan 3, 2025

• TangoFlux

  Public
  TangoFlux: Super Fast and Faithful Text to Audio Generation with Flow Matching

  Jupyter Notebook

  •

  MIT License

  •58•0•0•0•Updated Jan 2, 2025Jan 2, 2025

• AgiBot-World

  Public
  World's First Large-scale High-quality Robotic Manipulation Benchmark

  Jupyter Notebook

  •

  MIT License

  •91•0•0•0•Updated Dec 30, 2024Dec 30, 2024