Benchmark Almanac

AISHELL

We track 3 benchmarks that AISHELL made or helped make.

0 in use 0 with public code 2 with a leaderboard here

Benchmarks

Name Kind Released Best score Status
AISHELL-1 Models transcribe Mandarin read speech. Scored by character error rate. Speech recognition and translation Sep 2017 0.31% Dropped
AISHELL-2 Models transcribe 1,000 hours of Mandarin speech recorded on several devices. Scored by character error rate. Speech recognition and translation Aug 2018 2.56% Dropped
AISHELL-4 Models transcribe Mandarin meetings and identify speakers from conference recordings. NVIDIA reports character error after matching speakers. Speech recognition and translation Apr 2021 Not in cards