Open ASR leaderboard adds private Egyptian and Nigerian English data
What happened
On 6 November 2026, the Hugging Face Blog announced that Hugging Face's Open ASR Leaderboard, in partnership with Liva AI, has added private evaluation data for two English accents: Egyptian and Nigerian. The Egyptian accent data totals 1.34 hours and the Nigerian accent data 1.55 hours, both conversational spontaneous speech with transcripts that include punctuation, casing and disfluencies. The leaderboard also adds accent groupings based on the Kachru three-circles model, distinguishing US from non-US accents and inner-circle from outer- and expanding-circle accents. The private data has now been incorporated into the leaderboard's evaluation.
Written by AI from the reports · updated 28 min ago
Timeline
Follow the reports to see the event from each side.
- Hugging Face BlogEgyptian and Nigerian English join the Open ASR Leaderboard
Back to Articles A few months ago, we added private data to the Open ASR Leaderboard : 11 splits from Appen and DataOceanAI covering scripted and conversational speech from five accents ( blog ). The community response was great, with many highlighting the importance of held-out sets for trustworthy evaluations .
Heat of this event
Not enough continuous observations yet to draw a trend.