PrototypeCommon
howl-anderson/MicroTokenizer
一个轻量且功能全面的中文分词器，帮助学生了解分词器的工作原理。MicroTokenizer: A lightweight Chinese tokenizer designed for educational and research purposes. Provides a practical, hands-on approach to understanding NLP concepts, featuring multiple tokenization algorithms and customizable models. Ideal for students, researchers,…
- Owner
- howl-anderson (personal account)
- Stars
- Stars: 160
- Forks
- Forks: 22
- Language
- Python
- License
- MIT
- Created
- 2018
- Topics
- chinese-nlptokenizerchinese-tokenizerdag-networknlp-machine-learningchinese-word-segmentationeducational-project
- Tier
- Prototype (100 to 249 ★) What this tier means
More repos by howl-anderson
All 10 repos by howl-anderson- howl-anderson/unlocking-the-power-of-llmsStars: 2,469ShellRC
- howl-anderson/Chinese_models_for_SpaCyStars: 673Jupyter NotebookAlpha
- howl-anderson/agentsilexStars: 458PythonAlpha
- howl-anderson/hanzi_chaiziStars: 432PythonAlpha
- howl-anderson/hanzi_char_featurizerStars: 302PythonAlpha
- howl-anderson/tools_for_corpus_of_people_dailyStars: 293PythonAlpha
Nearby in Python
All Python repos- Video-Rebirth/hyperflowStars: 160PythonPrototype
- alexyc9381/hiring-panel-skillStars: 160PythonPrototype
- UnderleveledBuilder/awesome-social-media-skillsStars: 160PythonPrototype
- sethtrain/django-gitStars: 160PythonPrototype
- knipknap/GelatinStars: 160PythonPrototype
- niemeyer/hsandboxStars: 160PythonPrototype