NepSwor: Regional Languages
Preservation
Documenting and preserving the rich linguistic diversity of Nepal through technology and community collaboration
Our Approach
Parallel Corpus
1k sentences per language
Voice Data
High-quality recordings
Benchmark Data
ASR & Translation
Future Vision
4 lakh sentences
Featured Languages
Nepali
The official language of Nepal, spoken by 13,084,457 speakers (44.86% of the population).
Devanagari
Active
Maithili
An Indo-Aryan language spoken by 3,222,389 people (11.05% of the population).
Tirhuta
Vulnerable
Bhojpuri
A vibrant language spoken by 1,820,795 people (6.24% of the population).
Devanagari
Vulnerable
Tharu
A unique language spoken by 1,714,091 people (5.88% of the population).
Devanagari
Endangered
Tamang
A Tibeto-Burman language spoken by 1,423,075 people (4.88% of the population).
Devanagari
Vulnerable
Bajjika
A language spoken by 1,133,764 people (3.89% of the population).
Devanagari
Vulnerable
Avadhi
A language spoken by 864,276 people (2.96% of the population).
Devanagari
Vulnerable
Nepal Bhasha (Newari)
A Tibeto-Burman language spoken by 863,380 people (2.96% of the population).
Newari
Endangered
Magar Dhut
A Tibeto-Burman language with rich cultural heritage.
Devanagari
Vulnerable
Project Impact
Nepali languages supported
High-quality recordings
Educational materials
Active collaborations
Join Us
Help us advance Nepali language technology through collaboration and innovation