Reverse Dependencies of fugashi

The following projects have a declared dependency on fugashi:

• adapter-transformers — A friendly fork of HuggingFace's Transformers, adding Adapters to PyTorch language models
• augly-jp — Data Augmentation for Japanese Text
• bunruija — A text classification toolkit
• camphr-core — no summary
• cardbuilder — A package for programmatically generating language learning flashcards
• cody-adapter-transformers — A friendly fork of HuggingFace's Transformers, adding Adapters to PyTorch language models
• daaja — NLP data augmentation tool
• dooly — A library that handles everything with 🤗 and supports batching to models in PORORO
• dvg — document-vector grep
• epubhv — make your epub books vertical or horizontal.
• fonduer — Knowledge base construction system for richly formatted data.
• furigana4epub — A Python script to adding/removing furigana for Japanese epub books.
• Japanese-BPE-Tokenizer — Mecab-based BPE toknizer for Japanese text
• japre — Custom pretokenizers for Japanese language models
• jatool — A Python package for jatools
• JPFreq — A Python module which allows for the easy frequency analysis of Japanese text
• jshbtf0302 — State-of-the-art Natural Language Processing for TensorFlow 2.0 and PyTorch
• langcheck — Simple, Pythonic building blocks to evaluate LLM-based applications
• manga-ocr — OCR for Japanese manga
• manga-ocr-abang — OCR for Japanese manga
• mecab-text-cleaner — Simple Python package for getting japanese reading (yomigana) using MeCab
• mw-adapter-transformers — A friendly fork of HuggingFace's Transformers, adding Adapters to PyTorch language models
• ocr_translate-hugging_face — Plugins to enable usage of HuggingFace Models in ocr_translate
• opuscleaner — no summary
• shbtf0302 — State-of-the-art Natural Language Processing for TensorFlow 2.0 and PyTorch
• similar-documents — Generate similarity scores for documents from cli
• softchat — convert twitch/youtube chat into softsubs
• sumire — Scikit-learn compatible Japanese text vectorizer for CPU-based Japanese natural language processing.
• tablelinker-lib — A library of processes for manipulating tabular data in CSV format
• tf-shb-gabriel-0302 — State-of-the-art Natural Language Processing for TensorFlow 2.0 and PyTorch
• toiro — A comparison tool of Japanese tokenizers
• transformers — State-of-the-art Machine Learning for JAX, PyTorch and TensorFlow
• unidic-combo — UniDic2UD + COMBO-pytorch wrapper for spaCy
• url-text-module — Text Module of REACT
• voice100 — Voice100 is a small TTS for English and Japanese.
• xtts-api-server — A simple FastAPI server to host XTTSv2
• yomidict — Create frequency dictionaries for yomichan out of a variety of media
• yomigana-ebook — The fastest converter to add yomigana(readings) to Japanese epub eBooks! (Using Mecab and Unidic)
• yomikata — Japanese kanji disambiguation