Evaluating Multilingual LLMs at Scale
For Microsoft Research, Karya completed one of the largest multilingual human evaluations of LLMs within three weeks.
Mapping India’s Linguistic Diversity with Project Vaani
Project Vaani, a collaboration between Google and Indian Institute of Science, aims to map India's diverse linguistic landscape by collecting audio speech data from approximately 1 million people across 773 districts.
6000
hours of Voice Data
30
Districts
24K+
Unique Speakers
15
minutes/speaker
With Karya's expertise, 6000 hours of voice data will be gathered from 30 districts, contributing to one of the largest datasets of Indian dialects, totaling over 150,000 hours of audio upon completion. Karya plays a pivotal role in this initiative by mobilising local communities, training field coordinators, and ensuring fair compensation for data collectors, thus empowering local voices and fostering inclusivity.
Related
Conversational Data and Call Center Data Collection(2400 hours)
Collecting and validating conversational speech data across multiple domains in 11 languages for Microsoft