Seongmin Park

voxtral-mini-realtime-rs. Voxtral ASR & TTS running natively and in the browser. A Rust implementation of Mistral's Voxtral mini realtime ASR / TTS using the Burn ML framework

lectures. Material for gpu-mode lectures

voxtral.c. Pure C inference of Mistral Voxtral Realtime 4B speech to text model

qwen-asr. C inference for Qwen3-ASR 0.6b and 1.7b transcriptions models

parakeet.cpp. Ultra fast and portable Parakeet implementation for on-device inference in C++ using Axiom with MPS+Unified Memory

gophers. Free gophers

transformers-into-vaes. Code for "Finetuning Pretrained Transformers into Variational Autoencoders"

TorchLeet. Leetcode for Pytorch

A.X-4.0. SKT A.X LLM 4.0

NLWeb. Main reference implementation for NLWeb, implemented in Python.

dia. A TTS model capable of generating ultra-realistic dialogue in one pass.

beyond-nanogpt. Minimal and annotated implementations of key ideas from modern deep learning research.

og-equity-compensation. Stock options, RSUs, taxes — read the latest edition: www.holloway.com/ec

PageIndex. 📑 PageIndex: Document Index for Vectorless, Reasoning-based RAG

LLM_Foreign_Block. LLM 모델의 외국어 토큰 생성을 막는 코드 구현

awesome-mcp-servers. A collection of MCP servers.

MidiTok. MIDI / symbolic music tokenizers for Deep Learning models 🎶

sentsplit. A flexible sentence segmentation library using CRF model and regex rules

hama. 🦛 Hangul Morphological Analyzer

Machine-Learning. Cross Beat (xbe.at) - Your hub for python, machine learning and AI tutorials. Explore Python tutorials, AI insights, and more.

AgenticRAG-Survey. Agentic-RAG explores advanced Retrieval-Augmented Generation systems enhanced with AI LLM agents.

markitdown. Python tool for converting files and office documents to Markdown.

classic-jazz. A new kind of database that's distributed across your frontend, containers, serverless functions and its own storage cloud.

lmplay. A playground to make it easy to try crazy things

zig_gpt2. GPT-2 inference engine written in Zig

llama2.zig. Inference Llama 2 in one file of pure Zig

libonnx. A lightweight, portable pure C99 onnx inference engine for embedded devices with hardware acceleration support.

onnx2c. Open Neural Network Exchange to C compiler.

zml. Any model. Any hardware. Zero compromise. Built with @ziglang / @openxla / MLIR / @bazelbuild

SentenceVAE. Enable Next-sentence Prediction for Large Language Models with Faster Speed, Higher Accuracy and Longer Context

LoQT. Python

tokenlearn. Pre-train Static Word Embeddings

awesome-esp-rust. Curated list of resources for ESP32 development in the Rust programming language

zig-wasm-react-nodejs. A Zig Wasm Project to Document The Way You Can Create a Small WASM Binary and Use It With React & NodeJS

bad-licenses. A compendium of absurd "open-source" licenses.

zig-wasm-string-and-struct. Example of passing string between WASM host language and struct references to host

react-hotkey. Hotkey library for react

actionpower-rn-audio-recorder. Swift

daglo-ui. TypeScript

dagloapi-js-beta. JavaScript

huggingface_KoreanDataset. huggingface에 있는 한국어 데이터 세트

papeg_ai. Code for Papeg.ai

model2vec. Fast State-of-the-Art Static Embeddings

Gowun-Dodum. Korean fonts

zig-cookbook. Simple Zig programs that demonstrate good practices to accomplish common programming tasks.

wasm3. 🚀 A fast WebAssembly interpreter and the most universal WASM runtime

zigtoys. All about Zig + WASM and seeing what we can do

openai-elasticsearch-rag. Retrieval Augmented Generation (RAG) Application to offer Q&A like experience on a long format text using OpenAI and ElasticSearch as Vector DB.

g2p-seq2seq. G2P with Tensorflow

GenAI_Agents. 50+ tutorials and implementations for Generative AI Agent techniques, from basic conversational bots to complex multi-agent systems.

uroman. Universal Romanizer that can convert any unicode script to roman (latin) script

mteb_ko_leaderboard. 한글 텍스트 임베딩 모델 리더보드

OpenPhonemizer. An espeak-compatible, permissively-licensed IPA phonemizer (G2P) based on DeepPhonemizer. Usable as a drop-in replacement for espeak's GPL phonemizer.

CAT. CAT is more than a CRF-based ASR toolkit: it provides a complete workflow for data-efficient end-to-end ASR, supporting CTC, CTC-CRF, RNN-T, and language-model training and inference.

tinystatus. Tiny status page generated by a Python script

awesome-zig. 📜Zig Learning Guide & Project Lists

CMUdict. CMUdict maintenance, and tools

jetzig. Jetzig is a web framework written in Zig

supertree. Impress your boss with interactive Decision Tree visualization

courses. Anthropic's educational courses

spin. Spin is the open source developer tool for building and running serverless applications powered by WebAssembly.

NeMo-text-processing. NeMo text processing for ASR and TTS

Grapheme-to-Phoneme. Grapheme-to-Phoneme(G2P) 관련자료 모음

writefreely. A clean, Markdown-based publishing platform made for writers. Write together and build a community.

spice. Fine-grained parallelism with sub-nanosecond overhead in Zig

RAG_Techniques. This repository showcases various advanced techniques for Retrieval-Augmented Generation (RAG) systems. Each technique has a detailed notebook tutorial.

KoCommonGEN-V2. KoCommonGEN v2: A Benchmark for Navigating Korean Commonsense Reasoning Challenges in Large Language Models

evaluate-llm-on-korean-dataset. Performs benchmarking on two Korean datasets with minimal time and effort.

mc-old. Midnight Commander's repository

yournextstore. AI-Native Open-Source Next.js commerce. Powered by Stripe. Ultra fast with typesafe Commerce SDK. Built for AI development (Claude, Codex, Cursor).

microgrants. A list of microgrant programs for your good ideas

vimtutor-sequel. Vimtutor Sequel - Advanced Vim Tutor Lessons ⌨️

openSpeechToIntent. A simple, but performant framework for mapping speech directly to categories and intents.

Minimal_pairs_in_Korean. Why did nobody make this app already?

nanoT5. Fast & Simple repository for pre-training and fine-tuning T5-style models

treeseg. Hierarchical topic segmentation of meeting transcripts using embeddings and divisive clustering.

R2R. SoTA production-ready AI retrieval system. Agentic Retrieval-Augmented Generation (RAG) with a RESTful API.

openskill.py. Multiplayer Rating System. No Friction.

pyxel. A retro game engine for Python

kagome. Self-contained Japanese Morphological Analyzer written in pure Go

kanpyo. Japanese Morphological Analyzer written in Rust

pytorch-seq2seq. Tutorials on implementing a few sequence-to-sequence (seq2seq) models with PyTorch and TorchText.

clap-ipa. Keyword spotting and forced alignment in any language

inspectus. LLM Analytics

awesome-zig.

RNN-GRU-pure-numpy. implement RNN GRU in python pure numpy

onnxruntime.zig. Incomplete experimental Zig wrapper for ONNX Runtime with examples (Silero VAD, NSNet2)

zig-tflite. Zig binding for TensorFlow Lite

TorchScript. Load a TorchScript Model in C++ ~ JUSTIN MITCHΞLL

gpt4all.zig. ZIG build for a terminal-based chat client for an assistant-style large language model with ~800k GPT-3.5-Turbo Generations based on LLaMa

awesome-zig. A collaborative list of awesome Zig libraries and resources.

cosmopedia. Python

Typoon. 한글을 제대로 지원하는 텍스트 확장기. A text expander that fully supports Hangeul.

terminaltexteffects. TerminalTextEffects (TTE) is a terminal visual effects engine, application, and Python library.

JDD-Description. Ju-Dung-A-Li Driven Development

LlamaFactory. Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)

augmentoolkit. Create Custom LLMs

hf-spacerini. Plug-and-play Search Interfaces with Pyserini and Hugging Face

transducer-tutorial. Example code for a neural transducer model.

miracl. A large-scale multilingual dataset for Information Retrieval. Thorough human-annotations across 18 diverse languages.

CaR. Clustering and Ranking: Diversity-preserved Instruction Selection through Expert-aligned Quality Estimation

functionary. Chat language model that can use tools and interpret the results

text-dedup. All-in-one text de-duplication

API-Pack. Jupyter Notebook

russian_g2p. Accentor and transcriptor for Russian language

llm-datasets. Curated list of datasets and tools for post-training.

min-sized-rust. 🦀 How to minimize Rust binary size 📦 https://github.com/johnthagen/min-sized-rust

EasyLLMFeaturePorter. 1-Click is all you need.

Bunny. A family of lightweight multimodal models.

esp-skainet. Espressif intelligent voice assistant

g2ps. Data and code for grapheme-to-phoneme transducers in lots of languages

symspellpy-ko. symspellpy를 한글 특성에 맞춰서 수정한 라이브러리. 음소분해를 이용해 더 정확한 오타교정을 해준다.

open-parse. Improved file parsing for LLM’s

TripoSR. TripoSR: Fast 3D Object Reconstruction from a Single Image

allosaurus. Allosaurus is a pretrained universal phone recognizer for more than 2000 languages

hanja. 한자 사전

low_cost_robot. Python

transformer-vae-literature-review.

UTTER-MS9-meetingdata. data related to MS9

LibreChat. Enhanced ChatGPT Clone: Features Agents, MCP, Skills, DeepSeek, Anthropic, AWS, OpenAI, Responses API, Azure, Groq, o1, GPT-5, Mistral, OpenRouter, Vertex AI, Gemini, Artifacts, AI model switching, message search, Code Interpreter, langchain, DALL-E-3, OpenAPI Actions, Functions, Secure Multi-User Auth, Presets, open-source for self-hosting. Active

LogicKor. 한국어 언어모델 다분야 사고력 벤치마크

orpo. Official repository for ORPO

awesome-llm-list. An overview of Large Language Model (LLM) options

grok-1. Grok open release

rbloom. A fast, simple and lightweight Bloom filter library for Python, implemented in Rust.

i18n-spreadsheet-to-json. Generate and sync per-language i18n JSON files from a Google Sheets spreadsheet.

puter. 🌐 The Internet Computer! Free, Open-Source, and Self-Hostable.

hunspell-dict-ko. Korean spellchecking dictionary for Hunspell

openfortivpn. Client for PPP+TLS VPN tunnel services

gruut-ipa. Python library for manipulating pronunciations using the International Phonetic Alphabet (IPA)

ipa-dict. Monolingual wordlists with pronunciation information in IPA

wasi-nn. Neural Network proposal for WASI

arch-setup-for-dummies. For exceptional dummies like me

yazi. 💥 Blazing fast terminal file manager written in Rust, based on async I/O.

py-crf. Python implementation of linear-chain conditional random fields.

hangul_to_ipa. A dash app that transcribes 한글 into [hɑŋɡɯl].

base16. A Framework for building Themes

issues. 한국어 입력 이슈 트래커

awesome-hyprland. Awesome list for Hyprland [maintainer=@yavko]

catppuccin. 😸 Soothing pastel theme for the high-spirited!

keyd. A key remapping daemon for linux.

Hyprland. Hyprland is an independent, highly customizable, dynamic tiling Wayland compositor that doesn't sacrifice on its looks.

SoftLabelCCRF. Implementation of Soft-Label Chain Conditional Random Field for Phrase Grounding in PyTorch

DSL-TL. The official repository for the DSLCC-TL shared-task

tofi. Tiny dynamic menu for Wayland

nojambot. Korean Dad joker

text-generation-inference. IBM development fork of https://github.com/huggingface/text-generation-inference

honeybee. Official implementation of project Honeybee (CVPR 2024)

leaked-system-prompts. Collection of leaked system prompts

annotated-s4. Implementation of https://srush.github.io/annotated-s4

ui. A set of beautifully-designed, accessible components and a code distribution platform. Works with your favorite frameworks. Open Source. Open Code.

google_cloud_storage. Deno Library to upload files to GCS and obtain signed url

unstructured. Convert documents to structured data effortlessly. Unstructured is open-source ETL solution for transforming complex documents into clean, structured formats for language models. Visit our website to learn more about our enterprise grade Platform product for production grade workflows, partitioning, enrichments, chunking and embedding.

Kpop-lyric-datasets. A json Dataset with 25696 kpop songs. (2000 ~ 2023)

mteb. MTEB: State-of-the-art evaluation of embeddings across languages and modalities

mergekit. Tools for merging pretrained large language models.

korean_wordlist. korean wordlist

text-embeddings-inference. A blazing fast inference solution for text embeddings models

KF-DeBERTa. 카카오뱅크 & 에프엔가이드에서 학습한 금융 도메인 특화 언어모델

lobehub. 🤯 LobeHub is your Chief Agent Operator, organizing your agents into 7×24 operations by hiring, scheduling, and reporting on your entire AI team.

awesome-chatgpt-dataset. Unlock the Power of LLM: Explore These Datasets to Train Your Own ChatGPT!

mamba. Mamba SSM architecture

marker. Convert PDF to markdown + JSON quickly with high accuracy

chatgpt_system_prompt. A collection of GPT system prompts and various prompt injection/leaking knowledge.

GPTs. leaked prompts of GPTs

CoT-Igniting-Agent. This repository contains the paper list for the paper: Igniting Language Intelligence: The Hitchhiker's Guide From Chain-of-Thought Reasoning to Language Agents

vectordb. A minimal Python package for storing and retrieving text using chunking, embeddings, and vector search.

LLM-Trainer. Train LLMs by just modifying config files!

lq-lora. Python

EvolvingQA_benchmark. Code and Dataset release of "Carpe Diem: On the Evaluation of World Knowledge in Lifelong Language Models" (NAACL 2024)

STEERStyleTransfer. Python

MiniMA. Code for paper titled "Towards the Law of Capacity Gap in Distilling Language Models"

chrome-extension-svelte-typescript-boilerplate. Boilerplate for Chrome Extension Svelte Typescript project

filco. [Preprint] Learning to Filter Context for Retrieval-Augmented Generaton

WebExtensionTemplate. Create a browser extension for Chrome, Firefox and Safari in no time.

KoPolitic-Benchmark-Dataset. A New Korean Text Classification Benchmark for Recognizing the Politic Intents in Online Newspapers

PCFG-NAT. Code for NeurIPS 2023 paper "Non-autoregressive Machine Translation with Probabilistic Context-free Grammar".

Tell2Design. [ACL2023 Area Chair Award] Official repo for the paper "Tell2Design: A Dataset for Language-Guided Floor Plan Generation".

K-HATERS. Hate speech detection corpus in Korean, shared with EMNLP 2023 paper

fantom. 👻 Code and benchmark for our EMNLP 2023 paper - "FANToM: A Benchmark for Stress-testing Machine Theory of Mind in Interactions"

lm-human-preference-details. RLHF implementation details of OAI's 2019 codebase

rlhf-length-biases. Jupyter Notebook

RAGchain. Extension of Langchain for RAG. Easy benchmarking, multiple retrievals, reranker, time-aware RAG, and so on...

deep-chat. Fully customizable AI chatbot component for your website

react-chat-window. Intercom-style live chat window written in react

BAMBOO. Python

chrome-extension-boilerplate-react. A Chrome Extensions boilerplate using React 18 and Webpack 5.

plug-and-play-prompt-persona. P5: Plug-and-Play Persona Prompting for Personalized Response Selection (EMNLP 2023)

alignment-handbook. Robust recipes to align language models with human and AI preferences

basis-aware-threshold. Code for the paper "Closing the Curious Case of Neural Text Degeneration"

PangyoCorpora.

llm-meetup. Liner LLM Meetup archive

PickScore. Python

text-generation-inference. An Apache 2.0 fork of HuggingFace's Large Language Model Text Generation Inference

streaming-llm. [ICLR 2024] Efficient Streaming Language Models with Attention Sinks

chrome-extensions-samples. Chrome Extensions Samples

chat-bubble. Simple chatbot UI for the Web with JSON scripting 👋🤖🤙

sveltekit-adapter-chrome-extension. Sveltekit adapter for making chrome extensions

reasoning-teacher. Large Language Models Are Reasoning Teachers (ACL 2023)

instagraph. Converts text input or URL into knowledge graph and displays