Speaker-Attributed, Time-Stamped Transcription (SATS) aims to transcribe what is said and to precisely determine the timing of each speaker, which is particularly valuable for meeting transcription. Existing SATS systems rarely adopt an end-to-end formulation and are further constrained by limited context windows, weak long-range speaker memory, and the inability to output timestamps. To address these limitations, we present MOSS Transcribe Diarize, a unified multimodal large language model that jointly performs Speaker-Attributed, Time-Stamped Transcription in an end-to-end paradigm. Trained on extensive real wild data and equipped with a 128k context window for up to 90-minute inputs, MOSS Transcribe Diarize scales well and generalizes robustly. Across comprehensive evaluations, it outperforms state-of-the-art commercial systems on multiple public and in-house benchmarks.

翻译：说话人归属、时间戳转录旨在转录语音内容并精确确定每位说话人的时间信息，这对于会议转录尤为重要。现有的说话人归属、时间戳转录系统很少采用端到端架构，且进一步受到有限上下文窗口、长程说话人记忆能力弱以及无法输出时间戳的限制。为解决这些不足，我们提出了MOSS Transcribe Diarize，这是一个统一的多模态大语言模型，能以端到端的方式联合执行说话人归属与时间戳转录任务。该模型基于大量真实野外数据进行训练，并配备了128k的上下文窗口以处理长达90分钟的输入，具有良好的可扩展性和鲁棒的泛化能力。在全面的评估中，它在多个公开及内部基准测试上均超越了最先进的商业系统。