Hugging Face· PlatformCapability change

Adding Benchmaxxer Repellant to the Open ASR Leaderboard

Hugging Face adds private, high-quality English ASR datasets from Appen Inc. and DataoceanAI to the Open ASR Leaderboard to prevent benchmaxxing and improve evaluation trustworthiness. The leaderboard's average WER remains computed on public datasets by default, with an optional toggle to include private datasets.

From the source

Appen Inc. and DataoceanAI have provided high-quality English ASR datasets covering scripted and conversational speech over multiple accents. To prevent potential risks of benchmaxxing or test-set contamination, we will keep these datasets private for a high-quality measure of performance on multiple tasks.

huggingface.co

Announced

06 May 2026 00:00 UTC

Detected