Model有道孔子4R2T2
Confucius 4R2T2
An open-source streaming automatic speech recognition model released by NetEase Youdao, featuring a latency of 200–600 ms. It employs an append-only subtitle strategy in which recognized text is never retroactively modified. The model's source code is released under the Apache 2.0 license.
Timeline (last 90 days)
Sep 22
NetEase Youdao released the Confucius 4R2T2 streaming speech recognition model, with latency controlled between 200 and 600 milliseconds, adopting an append-only subtitle strategy, with code licensed under Apache 2.0 and open weights available for download.
Unverified50%