BrikerMan/Kashgari
Kashgari is a production-level NLP Transfer learning framework built on top of tf.keras for text-labeling and text-classification, includes Word2Vec, BERT, and GPT2 Language Embedding.
This tool helps NLP developers quickly build and deploy text processing models. It takes raw text data as input and outputs classifications (like sentiment or topic) or labeled entities (like names or locations). It's designed for data scientists and machine learning engineers working on natural language understanding tasks.
2,388 stars. No commits in the last 6 months. Available on PyPI.
Use this if you need to build robust text classification or entity recognition models quickly for production use, leveraging pre-trained language models like BERT.
Not ideal if you need a no-code solution or are looking for a general-purpose AI platform rather than a specialized NLP framework.
Stars
2,388
Forks
433
Language
Python
License
Apache-2.0
Category
Last pushed
Sep 03, 2024
Commits (30d)
0
Dependencies
6
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/nlp/BrikerMan/Kashgari"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related tools
DerwenAI/pytextrank
Python implementation of TextRank algorithms ("textgraphs") for phrase extraction
Tiiiger/bert_score
BERT score for text generation
asyml/texar
Toolkit for Machine Learning, Natural Language Processing, and Text Generation, in TensorFlow. ...
yohasebe/wp2txt
A command-line tool to extract plain text from Wikipedia dumps with category and section filtering
neuralmind-ai/portuguese-bert
Portuguese pre-trained BERT models