腾讯混元发布Hy ASR 3.0：多语言WER约3%
腾讯混元出了Hy ASR 3.0，多语言WER约3%，嘈杂音频也能转成干净文字，还懂方言。
腾讯混元发布Hy ASR 3.0预览版，基于Hy3语言大脑将语音识别与语义理解融合。
该模型在通用识别、上下文感知、多场景鲁棒性和方言覆盖等维度表现领先。官方公布多语言词错误率（WER）约为3%，能将嘈杂的真实世界音频转换成干净连贯的文本，并准确捕捉说话者意图。
AI that finally hears you. 👂 Hy ASR 3.0 preview drops today. Powered by Hy3’s language brain → precision ASR + deep semantic understanding Wins on: • general recognition • context awareness • multi-scenario robustness • dialect coverage Messy real-world audio? Clean, coherent transcripts that nail your intent. Open + internal benches: leading. Multilingual WER ≈ 3%. Voice just got an upgrade. 🔥 #HyASR S #TencentAI A #Hy3 y3📊 18 ⚡
This report is categorized under AITOP's "Models" desk, focusing on China's AI industry and domestic foundation model ecosystem. Within our cross-regional analytical framework, it directly maps to US-China foundation model benchmarks and commercialization comparison. Key entities and technical topics under continuous tracking include Hy ASR 3.0, 腾讯混元, Hy3, 语音识别.
Source attribution: curated from Hunyuan (@TXhunyuan).
