Tencent Hunyuan open-sources simultaneous interpretation large model Hy-SimulMT; measured response time is about three seconds
Tencent Hunyuan launched and open-sourced the simultaneous interpretation large model Hy-SimulMT on October 26. It supports real-time Chinese-to-English speech-to-speech translation and real-time voice cloning, with measured response times of approximately three seconds—under four to five seconds faster than human professional translators.
Return to original text
A short introduction is retained here; the full text from the source website is not reposted. For specific wording and subsequent updates, please refer to the original article.
Open AIHOT original