GRAAL-Research/deepparse
Deepparse is a state-of-the-art library for parsing multinational street addresses using deep learning
This tool helps businesses and organizations accurately break down multinational street addresses into their core components like street name, city, province, and postal code. You input raw, unparsed addresses, and it outputs structured address data. This is ideal for data entry specialists, logistics coordinators, CRM managers, or anyone dealing with large datasets of international customer or location addresses.
332 stars. Available on PyPI.
Use this if you need to reliably standardize and categorize street addresses from various countries, especially for improving data quality or integrating with other systems.
Not ideal if you primarily work with addresses from only one country and have simpler, less complex parsing needs.
Stars
332
Forks
33
Language
Python
License
LGPL-3.0
Category
Last pushed
Mar 01, 2026
Commits (30d)
0
Dependencies
13
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/GRAAL-Research/deepparse"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related frameworks
NVIDIA/TransformerEngine
A library for accelerating Transformer models on NVIDIA GPUs, including using 8-bit and 4-bit...
mlcommons/inference
Reference implementations of MLPerf® inference benchmarks
mlcommons/training
Reference implementations of MLPerf® training benchmarks
datamade/usaddress
:us: a python library for parsing unstructured United States address strings into address components
CMU-SAFARI/Pythia
A customizable hardware prefetching framework using online reinforcement learning as described...