The Open ASR Leaderboard Adds Its First Global South Language

The Open ASR Leaderboard Adds Its First Global South Language The Open ASR Leaderboard Adds Its First Global South Language Published August 28, 2026 Update on GitHub Upvote 59 Eric Bezzam bezzam Shobhit Banga Shobhitbanga VoiceArena Manas Dhir manasdhir04 VoiceArena Bhaskar Singh bhaskarJT VoiceArena Manmeet Kaur manmeet-voicearena VoiceArena Aaditya Pareek pareek-voicearena VoiceArena Walecha Amritansh8675 VoiceArena Sagar Jain sagarjain268380 VoiceArena Hanuman Sidh hanuman44420 VoiceArena Vanshika Chhabra vanshikachhabra-voicearena VoiceArena Voice Arena and Hugging Face partner to launch open ASR evaluation for Hindi and Indian English Benchmarks decide what gets built. A model that scores well on the Open ASR Leaderboard gets adopted and iterated on, while capabilities the leaderboard does not measure tend not to improve.

This ProductLaunch is relevant to the technology intelligence record because it involves GitHub, Hugging Face, Meta, Intel. The source article should remain the factual reference for follow-up coverage.

• The Open ASR Leaderboard Adds Its First Global South Language Published August 28, 2026 Update on GitHub Upvote 59 Eric Bezzam bezzam Shobhit Banga Shobhitbanga VoiceArena Manas Dhir manasdhir04 VoiceArena Bhaskar Singh bhaskarJT VoiceArena Manmeet Kaur manmeet-voicearena VoiceArena Aaditya Pareek pareek-voicearena VoiceArena Walecha Amritansh8675 VoiceArena Sagar Jain sagarjain268380 VoiceArena Hanuman Sidh hanuman44420 VoiceArena Vanshika Chhabra vanshikachhabra-voicearena VoiceArena Voice Arena and Hugging Face partner to launch open ASR evaluation for Hindi and Indian English Benchmarks decide what gets built.
• A model that scores well on the Open ASR Leaderboard gets adopted and iterated on, while capabilities the leaderboard does not measure tend not to improve.
• Much of the recent work on the leaderboard has gone into making the evaluation metrics more trustworthy: Held-out private splits .
• Benchmark-fitting analysis to quantify how much models are reproducing reference transcripts rather than transcribing solely on the audio.
• Closing the gaps in normalisers to ensure correct predictions/variants are not penalized.
• All of that makes one number (WER) harder to game.