Model Releases

Tencent Hunyuan releases Hy ASR 3.0 preview: speech recognition that truly understands context

Original title:Hy ASR 3.0 preview发布:真正懂上下文的语音识别

AI summary

Tencent Hunyuan released the next-generation speech recognition model Hy ASR 3.0 preview, based on the large language model Hy3 and MoE architecture, integrating high-precision recognition with semantic understanding. On open-source evaluation sets, it achieved a WER of 3.34% for Mandarin Chinese, 2.62% for English and 3.12% for Cantonese, and supports contextual error correction, hotword injection and scenarios such as high-noise whispering. The model is now available on the Tencent Cloud API and debuted for free on the Yuanbao App.

Key Takeaways

  • Tencent Hunyuan released the next-generation speech recognition model Hy ASR 3.
  • 0 preview,based on the large language model Hy3 and MoE architecture,integrating high-precision…
  • On open-source evaluation sets,it achieved a WER of 3.
  • 34% for Mandarin Chinese,2.
  • 62% for English and 3.

Quick Facts

Published
Updated
Source
公众号:腾讯混元
Category
Model Releases
AI score
65
Read the original Read the full article at the original source
Why it matters

将 LLM 语义理解融入语音识别,上下文纠错和热词注入降低了专业场景的接入成本,元宝已集成可体验。

Related entities

Source & copyright

This article is based on curated titles and AI summaries from the AIHOT public API, with attribution and links back. Original copyright remains with the original publishers and authors; this site does not mirror full texts.

Original article · AIHOT entry

How to Cite

When citing this article, keep the title, date, and permalink, and credit Orange News as the source.

Orange News: Tencent Hunyuan releases Hy ASR 3.0 preview: speech recognition that truly understands context. August 4, 2026. https://new.nat6.net/en/news/cmsee1mhf0nn6ro2em6rt7tr4/

View all →