Skip to main content

A Morphology-Aware NLP Toolkit for the Sindhi Language

Project description

🛡️ SindhiNLTK: Morphology-Aware NLP Toolkit for Sindhi

PyPI version License: MIT

SindhiNLTK is a high-performance Python library designed to solve "Subword Shattering" in Sindhi Language Processing. Standard multilingual models (like Llama-3 and mBERT) break unique Sindhi orthographic clusters into semantically meaningless tokens.

SindhiNLTK introduces a V3 Linguistic Shield—a hybrid Regex-BPE architecture—that protects the integrity of the 52-letter Sindhi alphabet, reducing the Token Fertility Rate from 4.15 to 1.06 and preserving 100% of aspirated digraphs.


🚀 Installation

pip install sindhinltk

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

sindhinltk-1.0.2.tar.gz (3.4 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

sindhinltk-1.0.2-py3-none-any.whl (4.4 kB view details)

Uploaded Python 3

File details

Details for the file sindhinltk-1.0.2.tar.gz.

File metadata

  • Download URL: sindhinltk-1.0.2.tar.gz
  • Upload date:
  • Size: 3.4 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.12.12

File hashes

Hashes for sindhinltk-1.0.2.tar.gz
Algorithm Hash digest
SHA256 e77c46e6198429d8a8d4188f1222f45339cde8eb8d3826eb749468a9b90afaa3
MD5 7826c34d4ee4ea1c1edcc710c2953e1a
BLAKE2b-256 c4ad6bf62c8e3b19e0ced2abd974e7566370455a43dd7716adb30bfe5ff04213

See more details on using hashes here.

File details

Details for the file sindhinltk-1.0.2-py3-none-any.whl.

File metadata

  • Download URL: sindhinltk-1.0.2-py3-none-any.whl
  • Upload date:
  • Size: 4.4 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.12.12

File hashes

Hashes for sindhinltk-1.0.2-py3-none-any.whl
Algorithm Hash digest
SHA256 51e105440a56ba4cf58b9e920c45e3722776445d31ccc68cd5c9f5efd8df6385
MD5 47cc85f22035408ee876de6fdbe9bdf5
BLAKE2b-256 c4358a67287587d0847e147b5af9d0a56f4febdf4405cedb96232b292c19d48c

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page