PulseAugur
EN
LIVE 12:26:19
中文(ZH) 腾讯混元Hy ASR 3.0 preview：让语音识别理解上下文

Tencent Hunyuan releases Hy ASR 3.0 preview with enhanced context understanding

By PulseAugur Editorial · [3 sources] ·

Tencent Hunyuan has released its new Hy ASR 3.0 preview, an advanced speech recognition model that integrates deep semantic understanding with high-accuracy voice recognition. This new model demonstrates significant improvements in general recognition, contextual awareness, multi-scenario robustness, and dialect coverage, achieving low word error rates on various benchmarks. The Hy ASR 3.0 preview is now available via API on Tencent Cloud and is being integrated into products like Yuanbao and WorkBuddy. AI

IMPACT Enhances AI applications by improving the accuracy and contextual understanding of speech recognition, potentially leading to more natural and efficient human-computer interactions.

RANK_REASON New model release from a major AI lab (Tencent Hunyuan). [lever_c_demoted from frontier_release: ic=2 ai=1.0]

Read on 量子位 (QbitAI) →

AI-generated summary · Google Gemini · from 3 sources. How we write summaries →

Tencent Hunyuan releases Hy ASR 3.0 preview with enhanced context understanding

COVERAGE [3]

  1. 量子位 (QbitAI) TIER_1 中文(ZH) · 允中 ·

    Tencent Hunyuan Hy ASR 3.0 preview: Making speech recognition understand context

    元宝已接入

  2. 36氪 (36Kr) TIER_1 中文(ZH) ·

    Tencent Hunyuan releases latest speech recognition model Hy ASR 3.0 preview

    36氪获悉，腾讯混元正式发布新一代语音识别模型Hy ASR 3.0 preview。在开源评测集中，Hy ASR 3.0 preview在多语种的WER（Word Error Rate, 词错误率）上都控制在3%左右，其中中文普通话WER 3.34%、英语WER 2.62%、粤语WER 3.12%。

  3. Mastodon — fosstodon.org TIER_1 한국어(KO) · [email protected] ·

    Tencent Hy (@TencentHunyuan) Hy ASR 3.0 preview has been released. Based on Hy3's language model, it enhances not only speech recognition accuracy but also context and meaning understanding, highlighting core performance in processing audio from various real-world environments and dialects, and robustness in multiple usage scenarios. http

    Tencent Hy (@TencentHunyuan) Hy ASR 3.0 프리뷰가 공개됐다. Hy3의 언어 모델을 기반으로 음성 인식 정확도뿐 아니라 문맥·의미 이해를 강화했으며, 다양한 실제 환경의 오디오와 방언 처리, 여러 사용 시나리오에서의 견고성을 핵심 성능으로 내세운다. https:// x.com/TencentHunyuan/status/20 84579829303615497 # asr # speechrecognition # ai # languagemodel

RELATED ENTITIES

RELATED TOPICS