So Miyagawa's repositories
annotorious-v2-selector-pack
Additional selection tools for Annotorious and the Annotorious OpenSeadragon plugin
camel
🐫 CAMEL: Communicative Agents for “Mind” Exploration of Large Scale Language Model Society
coptic-translator-backend
Utilities and notebook code used to parse data and create Coptic machine translation models.
coptic-translator-frontend
A frontend for a Coptic machine translation utility.
doccano
Open source annotation tool for machine learning practitioners.
KirishitanLigaturesFont
Font for displaying abbreviated ligatures found in Kirishitan Ban prints.
LAREX
A semi-automatic open-source tool for Layout Analysis and Region EXtraction on early printed books.
layout-dataset
NDL-DocLデータセット(資料画像レイアウトデータセット)
lingrex
Linguistic Reconstruction with LingPy
ndlkotenocr_cli
NDL古典籍OCRのアプリケーション
ndlngramdata
デジタル化資料から作成したOCRテキストデータのngram頻度統計情報のデータセット
ndlocr_cli
NDLOCRのアプリケーション
PaLM-rlhf-pytorch
Implementation of RLHF (Reinforcement Learning with Human Feedback) on top of the PaLM architecture. Basically ChatGPT but with PaLM
Prompt-Engineering-Guide-Japanese
🐙 Guides, papers, lecture, notebooks and resources for prompt engineering
tagger-part-of-speech
Part of speech tagger for Sahidic Coptic
whisper
Robust Speech Recognition via Large-Scale Weak Supervision