Tencent releases Hy-SimulMT for real-time speech translation
Tencent Hunyuan released Hy-SimulMT-30B-A3B under the Apache 2.0 license, with standard, FP8 and GGUF variants for Chinese-English simultaneous translation. The project also provides the SimulInfer inference service and SimulTrain training tools, while speech output and voice cloning require a configured TTS service. Tencent reports that the model achieved about three seconds of StreamLAAL on RealSI, but the cited latency, quality and voice-cloning results have not been independently verified here.
The release combines an open-weight model, deployment software and training resources for low-latency bidirectional Chinese-English speech translation, giving developers an end-to-end starting point for simultaneous translation systems.
tencent/Hy-SimulMT-30B-A3B-Interleave Translation • 30B • Updated 23 days ago • 751 • 17
library_name: transformers tags:
#Tencent Hunyuan#Hy-SimulMT-30B-A3B#Hy-SimulMT-30B-A3B-Interleave#SimulInfer#SimulTrain#Hy Translate App#RealSI