AI 实时听写终于能分清谁在说话
以前 AI 实时转写只能把声音变成文字，分不清谁说的；想分清得再跑一遍「声纹聚类」，慢半拍。这篇把两件事合成一个模型：声音按小块进来，边听边出「谁说了什么」，不用等整段说完，也不用额外步骤。7B 模型在五套测试集上转写错误率最低，13 项说话人归属测试里 12 项最好或并列最好。它不是你明天就能装进手机的东西，但实时语音助手、会议记录、同传这类场景，「边听边分人」是刚需，这是往前迈的一步。
📄 原文摘要(英文)
Traditional speaker-attributed ASR systems treated ASR and speaker diarization as two separate tasks. Recently, end-to-end models such as VibeVoice-ASR have unified the two tasks within a single model. However, existing unified models still mainly support offline recognition, making it difficult to meet the low-latency requirements of real-time voice assistants and agents. To tackle this issue, we present VibeVoice-ASR-Streaming, one of the first LLM-based end-to-end approaches to streaming speaker-attributed ASR. It interleaves fixed-size audio chunks, a small amount of lookahead audio and previous text. This allows the model to produce ''who said what'' as speech arrives, without a separate diarization stage. For transcription accuracy, our 7B model achieves the lowest average WER/CER across five evaluation sets. For speaker attribution, it achieves the best or tied-best on 12 of 13 evaluation settings. We release the 1.5B and 7B model weights together with inference code.