Hugging Face adds Hindi, Indian English to ASR leaderboard based on spontaneous speech
aftahi_ai · x · 2026-08-29
Hugging Face partnered with Voice Arena to add Hindi and Indian English to the Open ASR Leaderboard using the Monsoon dataset.
Key Points:
- Introduces Monsoon hi and Monsoon en-IN datasets, each with a public split for self-scoring and a private held-out split.
- Models are evaluated on spontaneous conversation rather than clean read prompts, reflecting how people actually speak.
- This addresses the benchmark gap for languages and accents, ensuring performance gaps in real-world conditions are visible.
Related event: Hugging Face Adds Hindi Speech Benchmarks to Open ASR Leaderboard(3 posts)→
More from Research
- DeepPhylo infers phylogenetic trees without unrealistic evolutionary assumptions — anshulkundaje · 2026-10-15
- Wander preprint explores graph foundation models via shared objective and random-walk interface — mmbronstein · 2026-10-15
- CHI Reviewer: AI Slop Is Real, but Unusually Rigorous Papers Still Getting Through — IanArawjo · 2026-10-15
- Into the Unknown: CMU benchmark finds 114 of 135 AI-written research papers fail integrity checks — arankomatsuzaki · 2026-10-15
- 8 non-negotiable principles for building AI that actually learns from experience — tokenbender · 2026-10-15
- Benchling launches Science Foundries: multiplayer agent swarms for end-to-end science workflows — nlarusstone · 2026-10-15