Fact · Languages and accents
12languages
The Vistaar benchmark collects publicly available Indian-language test sets across 12 languages, giving 59 computed word error rate values.
Checked against its source on October 17, 2026
In the source's own words
“comprises of publicly available benchmarks across 12 languages, leading to 59 computed WER values across benchmarks and languages”
Vistaar: Diverse Benchmarks and Training Sets for Indian Language ASR, Kaushal Santosh Bhogale et al., Interspeech 2023 (arXiv:2305.15386), 2023, Introduction.
Open the original- What it measures
- Vistaar brings together test sets for many languages so that models can be compared on the same data. It includes Hindi test sets from several domains.
- What it does not show
- Vistaar is a benchmark for researchers. Its test sets come from different sources and conditions, so the numbers are not directly comparable across languages.