1.openai / tiktoken
tiktoken is a fast BPE tokeniser for use with OpenAI's models.
+1,591 stars
from 18,001 · score 7.37
Trending repositories
Ranked by Attention Score: stars gained over the last 180 complete days
9 repositories by Attention Score · May 8, 2026 – Nov 3, 2026 (UTC)
2.explosion / spaCy
💫 Industrial-strength Natural Language Processing (NLP) in Python
- natural-language-processing
- data-science
- machine-learning
- python
- cython
- nlp
- +11 more
+634 stars
from 33,383 · score 6.45
+474 stars
from 34,756 · score 6.16
4.hankcs / HanLP
中文分词 词性标注 命名实体识别 依存句法分析 成分句法分析 语义依存分析 语义角色标注 指代消解 风格转换 语义相似度 新词发现 关键词短语提取 自动摘要 文本分类聚类 拼音简繁转换 自然语言处理
- nlp
- natural-language-processing
- hanlp
- pos-tagging
- dependency-parser
- text-classification
- +2 more
+432 stars
from 36,104 · score 6.07
5.nltk / nltk
NLTK Source
+238 stars
from 14,528 · score 5.48
6.microsoft / unilm
Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities
- nlp
- pre-trained-model
- unilm
- minilm
- layoutlm
- layoutxlm
- +14 more
+221 stars
from 22,016 · score 5.40
7.facebookresearch / fairseqArchived
Facebook AI Research Sequence-to-Sequence Toolkit written in Python.
+161 stars
from 32,049 · score 5.09
8.piskvorky / gensim
Topic Modelling for Humans
- gensim
- topic-modeling
- information-retrieval
- machine-learning
- natural-language-processing
- nlp
- +9 more
+160 stars
from 16,350 · score 5.08
9.flairNLP / flair
A very simple framework for state-of-the-art Natural Language Processing (NLP)
+82 stars
from 14,314 · score 4.42