English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Tools annual

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Improving ASR systems is necessary to make new LLM-based use-cases accessibleto people across the globe. In this paper, we focus on Indian languages, andmake the case that diverse benchmarks are required to evaluate and improve ASRsystems for Indian languages. To address this, we collate Vistaar as a set of59 benchmarks across various language and domain combinations, on which weevaluate 3 publicly available ASR systems and 2 commercial systems. We alsotrain IndicWhisper models by fine-tuning the Whisper models on publiclyavailable training datasets across 12 Indian languages totalling to 10.7Khours. We show that IndicWhisper significantly improves on considered ASRsystems on the Vistaar benchmark. Indeed, IndicWhisper has the lowest WER in 39out of the 59 benchmarks, with an average reduction of 4.1 WER. We open-sourceall datasets, code and models.

Vistaar: Diverse Benchmarks and Training Sets for Indian Language ASR