Ki Hoon Kim's repositories
approaches-to-diarisation
A testing repo to share code and thoughts on diarisation
asr-sd-pipeline
Speech recognition & diarisation solution with text alignment, deployed in AML pipelines
bunkai
Sentence boundary disambiguation tool for Japanese texts (日本語文境界判定器)
demucs
Code for the paper Hybrid Spectrogram and Waveform Source Separation
docker-avidemux
Docker container for Avidemux
faster-whisper
Faster Whisper transcription with CTranslate2
dockge
A fancy, easy-to-use and reactive self-hosted docker compose.yaml stack-oriented manager
fastText
Library for fast text representation and classification.
JellyFlix
Jellyfin but Looks, Feels and Smells like Netflix
kiwipiepy
Python API for Kiwi
kss
Kss: A Toolkit for Korean sentence segmentation
langchain-tutorials
Overview and tutorial of the LangChain Library
MeloTTS
High-quality multi-lingual text-to-speech library by MyShell.ai. Support English, Spanish, French, Chinese, Japanese and Korean.
moonlight-qt
GameStream client for PCs (Windows, Mac, Linux, and Steam Link)
NeMo
NeMo: a toolkit for conversational AI
PyDeepLX
A Python package for unlimited DeepL translation
PyKakaoDBBot
Python Kakao Database Bot with Redroid & Android Chatbot
reverse-proxy-confs
These confs are pulled into our SWAG image: https://github.com/linuxserver/docker-swag
rvc-tts-pipeline
TTS pipeline that uses RVC to enhance audio quality and cloning
Sudachi
A Japanese Tokenizer for Business
Sunshine
Self-hosted game stream host for Moonlight.
upptime
⬆️ GitHub Actions uptime monitor & status page by @AnandChowdhary
uptime-kuma
A fancy self-hosted monitoring tool
weblangchain
LangChain-powered web researcher chatbot. Searches for sources on the web and cites them in generated answers.
whisper-at
Code and Pretrained Models for Interspeech 2023 Paper "Whisper-AT: Noise-Robust Automatic Speech Recognizers are Also Strong Audio Event Taggers"
whisper-ctranslate2
Whisper command line client compatible with original OpenAI client based on CTranslate2.
YouTokenToMe
Unsupervised text tokenizer focused on computational efficiency