发表机构
Index LLM Team（Index LLM 团队）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
Index-Translate是一个多语言翻译模型家族，通过共享基础与专门训练结合，在通用、语音、配音和长文档翻译上达到前沿性能。
AI 中文摘要
我们推出Index-Translate，这是一个多语言翻译模型家族，它将共享的多语言基础与针对通用翻译、指令遵循、语音翻译、受控配音和长文档翻译的专门训练相结合。该家族包含三个模型规模：2B、9B和35B-A3B，支持150种语言的翻译，并具备多语言指令遵循能力。在通用翻译和复杂翻译指令上的评估表明，Index-Translate优于同等规模的翻译模型，并达到与100B级翻译模型及前沿模型相当的性能。Index-Echo提供端到端的语音到文本和语音到语音翻译，优于现有端到端模型，并达到与前沿全能模型相当的性能。Index-Homura将该家族扩展至音节受控配音。Index-NativeLong引入了原生长文档翻译，配有专门的任务设定和基准。这些能力支持多样化的翻译任务，包括多语言内容生产。
英文摘要
We introduce Index-Translate, a multilingual translation model family that combines a shared multilingual foundation with specialized training for general translation, instruction following, speech translation, controlled dubbing, and long-document translation. It includes three model sizes, 2B, 9B, and 35B-A3B, and supports translation in 150 languages, with multilingual instruction following. Evaluations on general translation and complex translation instructions show that Index-Translate outperforms translation models of comparable size and achieves performance comparable to 100B-scale translation models and frontier models. Index-Echo provides end-to-end speech-to-text and speech-to-speech translation, outperforming existing end-to-end models and achieving performance comparable to frontier omni models. Index-Homura extends the family to syllable-controlled dubbing. Index-NativeLong introduces native long-document translation with a dedicated task formulation and benchmark. These capabilities support diverse translation tasks, including multilingual content production.
Comments27 pages. Project: https://index-translate.bilibili.com ; Code and models: https://github.com/bilibili/Index-Translate
