FlashNEWS BRIEFING

Tencent Hunyuan Launches New Speech Recognition Model Hy ASR 3.0 Preview

1 min read

88Z AI, 5 August — Tencent Hunyuan has released the new Hy ASR 3.0 preview speech recognition model. Built on the Hy3 large language model, it deeply integrates speech recognition with deep semantic understanding. The model achieves top-tier industry accuracy in Mandarin, English, and Cantonese scenarios, featuring intelligent error correction in complex contexts.

At a glance

  • Built on Hy3 LLM, integrating speech recognition with semantic understanding
  • Top-tier accuracy in Mandarin, English, and Cantonese with complex context error correction
Cover image for Tencent Hunyuan Launches New Speech Recognition Model Hy ASR 3.0 Preview
Cover image for Tencent Hunyuan Launches New Speech Recognition Model Hy ASR 3.0 Preview

The update

Tencent Hunyuan has officially launched the new generation speech recognition model, Hy ASR 3.0 preview. Built upon the Hy3 large language model, it achieves a deep integration of speech recognition technology with deep semantic understanding capabilities. This architectural innovation significantly enhances the model's performance across various language environments. In practical applications, Hy ASR 3.0 preview has reached top-tier industry accuracy levels in key scenarios including Mandarin Chinese, English, and Cantonese. Furthermore, the model possesses robust intelligent error correction capabilities, effectively handling recognition challenges in complex contexts to ensure the accuracy and reliability of output results.

Sources & editorial note

This article is an AI-assisted synthesis by 88Z AI based on the public sources below. Product claims and availability are attributed to their publishers. It does not represent independent testing or first-hand reporting.

  1. 腾讯混元Source published

Source dates above refer to the original announcements; the date under the headline is this article’s publication on 88Z AI.

Related reading

All stories
88Z.ai