sarvamai/indic-numtowords

sarvamai/indic-numtowords

Description: A simple lightweight library for text normalization for Indian Languages

Language: Python

License: MIT

Stars: 0

Forks: 2

Open issues: 0

Created: 2024-12-18T09:51:18Z

Pushed: 2026-04-15T19:46:25Z

Default branch: master

Fork: yes

Parent repository: AI4Bharat/indic-numtowords

Archived: no

README:

AI4Bharat num2words

> A module to convert numbers to words for Indian languages and English.

Installation

To install the module, run the following command:

pip install indic-numtowords

Import

To use the library, import it using the following command:

from indic_numtowords import num2words

Usage

1. Converts numbers into words in various languages:

words = num2words(38, lang='ta')
#output: 'முப்பத்து எட்டு'

2. Returns variations for numbers:

words = num2words(150, lang='hi', variations=True)
#output: ['एक सौ पचास', 'डेढ़ सौ']

3. Converts each digit separately:

words = num2words(420, lang='doi', split=True)
#output: 'चार दो सिफर'

Parameters

The num2words function accepts the following parameters:

• `number`: (int) The non-negative integer to convert into words.
• `lang`: (str) The ISO code for the target language. Defaults to English (en).
• `variations`: (bool, optional) If set to True, returns variations of the number.
• `split`: (bool, optional) If True, converts each digit separately into its word form.

Supported Languages

The following languages are supported by the num2words module:

• `as`: Assamese
• `bn`: Bengali
• `brx`: Bodo
• `doi`: Dogri
• `en`: English
• `gu`: Gujarati
• `hi`: Hindi
• `kn`: Kannada
• `ks`: Kashmiri
• `kok`: Konkani
• `mai`: Maithili
• `ml`: Malayalam
• `mr`: Marathi
• `mni`: Manipuri
• `ne`: Nepali
• `or`: Odia
• `pa`: Punjabi
• `sa`: Sanskrit
• `sd`: Sindhi
• `ta`: Tamil
• `te`: Telugu
• `ur`: Urdu

Release Notes

This package contains work on converting numbers to words. The contents of this package can also be downloaded from our GitHub repo.

Meta

Distributed under the MIT license. See LICENSE for more information.