腾讯已开源其Hy-SimulMT模型，这是一个语音到语音的翻译系统。该模型能够近乎实时地在中文和英文之间进行翻译，并保留原说话者的声音。腾讯报告称，对于较长的语音片段，其延迟约为3秒。 AI
影响 此次开源发布可能会推动实时语音翻译能力和语音克隆技术的发展。
排序理由 该集群描述了一个新的语音翻译模型的开源。 [lever_c_demoted from research: ic=1 ai=1.0]
AI 生成摘要 · Google Gemini · 来自 1 个来源。 我们如何撰写摘要 →
腾讯开源Hy-SimulMT实时语音翻译器
本文如何被排名
- Signal score
- 45 / 100
- Composite score across the factors below. Higher = stronger signal that this story matters right now.
- Newsworthiness bucket
- Tool
- 该集群描述了一个新的语音翻译模型的开源。 [lever_c_demoted from research: ic=1 ai=1.0]
- Source corroboration
- Single-source cluster
- Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
- Topics
- model release, product
- Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
- AI-industry relevance
- High
- Clearly on-topic for AI-industry coverage.
- Story freshness
- Breaking (< 6h)
- Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.
完整方法见我们的编辑标准。
报道来源 [1]
-
Tencent Hunyuan 开源 Hy-SimulMT，一款延迟约3秒的语音到语音翻译器
Hy-SimulMT translates Chinese and English speech in real time in the speaker's own voice. Tencent puts its official StreamLAAL latency at about 3 seconds on long-form speech.