Tencent releases Hy-SimulMT: real-time speech-to-speech translation with ~3s latency
_akhaliq · x · 2026-10-28
Tencent released Hy-SimulMT on Hugging Face, a real-time simultaneous translation model streaming Chinese↔English speech-to-speech with voice cloning and roughly 3 seconds of latency.
Per the benchmark chart, Hy-SimulMT sits at the quality-latency frontier (85 GEMBA at 3s StreamLAAL), beating Qwen3.8-LiveTranslate, GPT-Realtime-Translate, Gemini3.5-LiveTranslate and Seed-LiveInterpret 2.0, which are either slower or lower quality.
More from Models
- Open model Flint hits #2 trending on Hugging Face, team outlines next steps — josh_tobin_ · 2026-10-28
- YacineMTB rails: even the best LLMs are 'complete dogshit' and he's tired of it — yacineMTB · 2026-10-28
- Omni-InteractScope benchmarks proactive interaction in continuous omnimodal streams — Qwen · 2026-10-28
- Mistral releases Timestral time-series foundation models, tops GIFT-Eval — mistralai · 2026-10-28
- Gemini 4 Argon Hits 1.73% WER on OCR Benchmark, Surpassing Human Experts — gabriberton · 2026-10-28
- Meta's Omnilingual MT covers 1,600 languages, 1B–8B models rival 70B LLMs — kalyan_kpl · 2026-10-28