Tencent Hunyuan open-sources Hy-SimulMT, a live speech interpreter with about 3 seconds of lag
AITencent Hunyuan has open-sourced Hy-SimulMT, a model that translates Chinese and English speech into the other language in real time while cloning the speaker's voice. Tencent reports about 3 seconds of latency on the RealSI benchmark using the StreamLAAL metric, which the project notes is not the same as time to first translated speech.
AIWhy it matters.
The article gives the model's latency, benchmark scores, and the caveat on the StreamLAAL metric, helping readers weigh how it compares with human interpreters.
Loading source posts…
Source details
Pandaily · contact@pandaily.com (Pandaily) · pandaily.comPublished · added here
Original title: Tencent Hunyuan Open-Sources Hy-SimulMT, a Speech-to-Speech Interpreter With About 3 Seconds of Lag