最有价值项目

A simple iOS App that can convert speech/voice into text. Only English voice is supported for now. Used Swift 5, AVKit and Speech.

Windows app which allows efficient work on a computer by speech alone.

Pluggable real-time audio conversation framework for .NET. Local VAD, STT, TTS, and LLM

Long audio alignment using Kaldi

The Odin Tabs extension is a browser extension that allows you to navigate through your browser tabs using speech recognition and the Large Language Model (LLM) of your choice.

This repository reports how to build a speech to text model to recognize short commands. Best of all, developing and including speech recognition in a Python project using Keras is really simple.

Free, open-source Whisper desktop app — 100% offline speech-to-text for Windows, macOS & Linux. No cloud, no subscription.

🎹 Instruct.KR 2025 Summer Meetup: 오픈소스 LLM, vLLM으로 Production까지 🎹

NVFP4 inference on Blackwell GeForce (RTX 5090/5080/5070 Ti/RTX PRO 6000) — SM120 patches for vLLM + FlashInfer + CUTLASS. 175 tok/s on Qwen3.6-35B MoE.

Open-source, self-hosted AI workspace for local and open-weight LLMs with vLLM, LiteLLM, autonomous agents, MCP tools, deep research, artifacts, and BYOK.

An open-source, model-agnostic agent harness for local LLMs. Define agents in YAML (tools, memory, deny-first permissions) and run them against any OpenAI-compatible endpoint: vLLM, Ollama, LM Studio, or llama.cpp.

Over 60 figures and diagrams of LLMs, quantization, low-rank adapters (LoRA), and chat templates FREE TO USE in your blog posts, slides, presentations, or papers.

The Ultimate Developer Experience Platform for the Container Era

Train an LLM to generate cracked Manim animations for mathematical concepts.

Interview prep for LLM post-training, ML, system design, and coding — organized by career path.

🥉 Codalab-Microsoft-COCO-Image-Captioning-Challenge 3rd place solution(06.30.21)

Build a Large Language Model From Scratch

CyberBrain_Model is an advanced AI project designed for fine-tuning the model `DeepSeek-R1-Distill-Qwen-14B` specifically for cyber security tasks.

Code for TR2-D2: Tree Search Guided Trajectory-Aware Fine-Tuning for Discrete Diffusion

IntelliJ IDEA plug-in that will help you to quickly create Merge Requests for GitLab