Back to Home
RadarAI··Papers & Tech

Nvidia 发布开源语音分离模型 Nemotron 3 Diarization,实时区分最多八位说话人

中文摘要

Nvidia发布开源Nemotron 3 Diarization模型,可实时区分最多8位说话人并检测重叠语音。

English Summary

Nvidia released open-source Nemotron 3 Diarization, capable of distinguishing up to eight speakers in real-time and detecting overlapping speech.

Original Excerpt

Nvidia 发布约 100M 参数的 Nemotron 3 Diarization 模型,权重免费开放,可实时区分最多八位说话人并检测重叠语音,支持录音和实时音频。