Open ASR Leaderboard adds Egyptian and Nigerian English accents
The Open ASR Leaderboard has expanded its private data sets to include two new accents: Egyptian and Nigerian English. This addition follows a previous collaboration with Voice Arena for Indian-accented English and earlier integrations with Appen and DataOceanAI. The new data comes from Liva AI, which collects multimodal interaction data through consumer products used by real people.
Key points
- New private data splits for Egyptian and Nigerian accents added to the Open ASR Leaderboard.
- Liva AI provides the data, collected via consumer products used by real people.
- Leaderboard now reports results using Kachru’s Three Circles framework for accent breakdowns.
The leaderboard will now report performance using a framework based on Kachru’s Three Circles, credited to Hume AI. This allows for a breakdown comparing US English against non-US English (UK, Australia, Canada, India, Nigeria, Egypt) and Inner Circle accents against Outer and Expanding Circles. The goal is to improve representation in automatic speech recognition evaluations and reduce overfitting to public benchmarks by using held-out private data.
Liva AI provides this data by designing products around specific model gaps, allowing for the collection of natural, high-context behavior from real product use rather than artificially elicited interactions. This collaboration aims to make ASR evaluations more trustworthy and representative of global speech patterns.
Egyptian and Nigerian English join the Open ASR Leaderboard
Hugging Face · 6 November 2026
Loading the full article…
This text was published by Hugging Face and written by Eric Bezzam. It is reproduced here with attribution so you can read it in full; the rights remain with the publisher. Read it at the source ↗
The headline, key points and digest above were generated by Digest AI's editorial model from the linked sources. Automated summaries can contain errors: the sources are the record. Spotted a mistake? Tell us. Published by Martin K., who runs Digest AI and handles corrections.
More in Research
All →- Researchers propose closed-loop agent evaluation method for deployed AI systems · 1 src
- Researchers propose framework for AI-directed evolution and safety risks · 1 src
- Researchers propose TRAP policy for AI agent authorization · 1 src
- Researchers autoformalize linear regularization theory in Lean with AI agents · 2 src
- Researchers propose Two-Ledger Model for tracking AI costs in enterprise transactions · 1 src
Comments
via GitHub Discussions