A fast and soft pattern search for trillion-scale corpora.
☆239Feb 28, 2026Updated 7 months ago
Alternatives and similar repositories for softmatcha2
Users that are interested in softmatcha2 are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- ⚡Japanese sentence splitting(日本語文境界判定器), 40–250× faster via a Rust-accelerated Python library with near-perfect API compatibility with …☆77Oct 14, 2025Updated last year
- ☆41Oct 21, 2025Updated 11 months ago
- ☆15Sep 30, 2026Updated 2 weeks ago
- Swallowプロジェクト 事後学習済み大規模言語モデル 評価フレームワーク☆34May 8, 2026Updated 5 months ago
- A simple integer compression library for C/C++/Java☆14Feb 25, 2013Updated 13 years ago
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- YomiTokuはAIを活用した日本語文書解析エンジンを提供するPythonパッケージです。 Yomitoku is an AI-powered document image analysis package designed specifically for the Ja…☆1,624Updated this week
- ☆16Jan 3, 2025Updated last year
- ☆352Oct 10, 2026Updated last week
- Python package for LLM compression☆436Updated this week
- A tool for visualizing the internal structures of morphological analyzer Sudachi☆18Jun 9, 2022Updated 4 years ago
- The evaluation scripts of JMTEB (Japanese Massive Text Embedding Benchmark)☆94Oct 9, 2026Updated last week
- 🛥 Vaporetto: Very accelerated pointwise prediction based tokenizer☆299Oct 10, 2026Updated last week
- Python binding for Lindera.☆18Mar 28, 2026Updated 6 months ago
- Fine-tuning Moshi/J-Moshi on your own spoken dialogue data☆106Jan 5, 2026Updated 9 months ago
- Managed hosting for WordPress and PHP on Cloudways • AdManaged hosting for WordPress, Magento, Laravel, or PHP apps, on multiple cloud providers. Deploy in minutes on Cloudways by DigitalOcean.
- A soft and fast pattern matcher for billion-scale corpora.☆75Feb 26, 2025Updated last year
- Preferred Generation Benchmark☆109Aug 31, 2026Updated last month
- Official implementation of "TAID: Temporally Adaptive Interpolated Distillation for Efficient Knowledge Transfer in Language Models"☆126Oct 6, 2025Updated last year
- NDLOCR-Liteアプリケーションのリポジトリ（ソースコードを含む）NDLOCR‑Lite application repository (including source code)☆1,353Oct 8, 2026Updated last week
- Japanese synonym library☆55Feb 7, 2022Updated 4 years ago
- Sentence boundary disambiguation tool for Japanese texts (日本語文境界判定器)☆200Mar 26, 2024Updated 2 years ago
- Ultimate transpiler: converts Python to C++, Rust, C#, PowerShell, JavaScript, TypeScript, Dart, Go, Java, Swift, Kotlin, Ruby, Lua, Sca…☆302May 3, 2026Updated 5 months ago
- DIRECT: Direct and Indirect REsponses in Conversational Text Corpus☆17Jul 1, 2021Updated 5 years ago
- Simpler 1Password CLI. Auto-finds .env, injects secrets.☆76Feb 23, 2026Updated 7 months ago
- Managed hosting for WordPress and PHP on Cloudways • AdManaged hosting for WordPress, Magento, Laravel, or PHP apps, on multiple cloud providers. Deploy in minutes on Cloudways by DigitalOcean.
- 直観主義の命題論理+自然演繹の中で与えられた定理を検証する遺伝的アルゴリズムを用いた証明探索エンジン☆19Mar 11, 2026Updated 7 months ago
- ☆35Oct 10, 2026Updated last week
- Funer is Rule based Named Entity Recognition tool.☆22Apr 21, 2022Updated 4 years ago
- 慶応義塾大学 理工学部 情報工学科 講義「自然言語処理」☆19Jul 15, 2026Updated 3 months ago
- [ICLR 2026] Evaluating the performance of LLMs on Japanese challenging financial tasks.☆37Mar 6, 2026Updated 7 months ago
- FLAIR: Factored Level And Interleaved Ridge - single-equation time series forecasting☆82May 12, 2026Updated 5 months ago
- Step-oriented resumable batch execution for Node.js and browsers using SQLite☆20Oct 10, 2026Updated last week
- AJIMEE-Bench (Advanced Japanese IME Evaluation Benchmark)☆27Jan 13, 2025Updated last year
- Reversi solver on Rust☆11Aug 9, 2026Updated 2 months ago
- Managed hosting for WordPress and PHP on Cloudways • AdManaged hosting for WordPress, Magento, Laravel, or PHP apps, on multiple cloud providers. Deploy in minutes on Cloudways by DigitalOcean.
- This repository contains the training and evaluation code for llm-jp-modernbert-base.☆17Jun 17, 2025Updated last year
- J-Moshi: A Japanese Full-duplex Spoken Dialogue System☆324Sep 13, 2026Updated last month
- デジタル化資料OCRテキスト化事業において作成されたOCR学習用データセット☆82Jun 26, 2024Updated 2 years ago
- Line shuffler for huge text file which does not fit in memory☆13Sep 7, 2026Updated last month
- Python tool for automated evaluation of generation☆64Sep 29, 2026Updated 2 weeks ago
- 『Kaggle ではじめる大規模言語モデル入門 ～自然言語処理〈実践〉プログラミング～』のサポートサイト☆42Jul 5, 2026Updated 3 months ago
- textlintプリセット：AIっぽい記述パターンを検出し、より自然な日本語表現を促すルール集☆1,156Jun 16, 2026Updated 4 months ago