MosiAI 新发的 0.9B 开源模型，一次性搞定多人对话的转录、打标签和加时间戳，90 分钟音频都不用分块，还支持关键词纠偏，赶紧试试。
MosiAI 发布了 MOSS-Transcribe-Diarize-0.9B，一个 0.9B 参数的开源端到端模型，专门用于多说话人长音频转录。该模型将 ASR、说话人日记化和时间戳对齐整合为单个生成式过程，不同于 WhisperX 的分阶段串联方式。它支持最长约 90 分钟的音频一次性输入，无需分块或拼接，并具备关键词偏置功能以提升专有名词识别准确率。vLLM 在发布当天（day-0）即提供了对该模型的支持。
🎉 Congrats to the @MosiAI_Official team on MOSS-Tr…
🎉 Congrats to the @MosiAI_Official team on MOSS-Transcribe-Diarize-0.9B, an open, end-to-end model for multi-speaker long-audio transcription, with day-0 support in vLLM.
Most setups chain ASR + diarization + alignment (WhisperX-style). This one does all three in a single generative pass. It transcribes the speech, tags who is speaking, and emits timestamps together:
[0.11][S01] Good morning![1.03] [1.11][S02] Morning, guys![1.34]
A Whisper-style audio encoder feeds a Qwen3-style causal decoder, so a recording up to ~90 minutes goes in as one shot, no chunking or stitching. Keyword biasing lets you prime names, product codes, and domain terms so proper nouns come out right. Useful for meeting notes, interviews, call-center QA, and podcast transcription.
🔗 https://t.co/tTBqjY3vrL
- LMSYS Org (SGLang)07-10 14:17原文