Categories Companies Research

Loading the SOTA2 catalog…

Explore

Categories Companies Research

Contribute

Join SOTA2 Contact

SOTA2

© 2026 SOTA2

Build in Bellevue, USA

WizWand is now SOTA2 Research

Papers Benchmarks Datasets Tasks

Speech-to-Text research benchmarks · SOTA2 Research

Speech-to-Text

Benchmarks

Dataset NameSOTA MethodSort

Dataset NameSOTA methodMetricTrendResultsLast Updated

4.78AlpacaEval Score

15

Feb 26, 2026

Multilingual Speech-to-Text dataset Education groups

22.28WER (>= Graduate)

12

Jun 26, 2026

Multilingual Speech-to-Text dataset Occupation groups

41.18Patient WER

12

Jun 26, 2026

Multilingual Speech-to-Text dataset Gender groups

37.25WER (Male)

12

Jun 26, 2026

Multilingual Speech-to-Text Kannada

52.84WER

12

Jun 26, 2026

Multilingual Speech-to-Text dataset Hindi

32.96WER

12

Jun 26, 2026

Multilingual Speech-to-Text dataset English

20.43WER

12

Jun 26, 2026

Multilingual Speech-to-Text dataset Overall

35.19WER

12

Jun 26, 2026

LibriSpeech LS960 (test-other)

9.2WER

6

May 29, 2026

LibriSpeech LS960 (dev clean)

3.6WER

6

May 29, 2026

Popular datasets

Multilingual Speech-to-Text dataset LibriSpeech VoiceBench Multilingual Speech-to-Text

Follow for updates

Join SOTA2 Contact