Skip to content

BnGraphemizer: A Grapheme-based Tokenizer for Bengali Handwritten Text Recognition. This implementation utilizes Trie for fast and efficient tokenization.

Notifications You must be signed in to change notification settings

JahidBasher/BnGraphemizer

Repository files navigation

BnGraphemizer: Bengali TRIE-based tokenizer

  • To be used in Text Recognition, Speech Recognition, Text to Speech Generation System
  • It works on 'provided' set of vocabulary, making it useful for many NLP systems

How BnGraphemizer Works

Installation

Run pip install git+https://github.com/Jahid006/BnGraphemizer to install the package directly

Related papers: BnGraphemizer: A Grapheme-based Tokenizer for Bengali Handwritten Text Recognition

About

BnGraphemizer: A Grapheme-based Tokenizer for Bengali Handwritten Text Recognition. This implementation utilizes Trie for fast and efficient tokenization.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published