Tencent releases Hy-SimulMT, a real-time Chinese-English simultaneous translation model
AITencent Hunyuan has released Hy-SimulMT, a real-time simultaneous translation model for bidirectional Chinese-English speech-to-speech translation with real-time voice cloning. In the RealSI long-form audio evaluation, the company reports a StreamLAAL of about 3 seconds, the lowest among the systems shown, and a GEMBA score above the compared open-source models and four of five commercial APIs.
AIWhy it matters.
The release page documents latency and quality results against open-source models and commercial APIs, plus the setup path, helping readers judge real-time Chinese-English translation.
Source details
Tencent · new models on Hugging Face · huggingface.coPublished · added here
Original title: tencent/Hy-SimulMT-30B-A3B-Interleave