NVIDIA 发布 Nemotron 3 Diarization 说话人分离模型
When several people talk at once, a transcript can get messy fast. Our new Nemotron 3 Diarization m...
精选理由
NVIDIA 出了个 100M 参数的小模型，专门搞定多人说话分不清谁是谁的问题，8 人以内、说话重叠都能识别，已经上了 Hugging Face。
NVIDIA 推出 Nemotron 3 Diarization 模型，用于解决多人同时说话时转录混乱的问题。该模型参数量为 100M，支持最多 8 个说话人，在声音重叠的情况下也能追踪谁在什么时间说话。模型现已上架 Hugging Face，可直接下载使用。
原文 · NVIDIA AI
When several people talk at once, a transcript can get messy fast. Our new Nemotron 3 Diarization m...
When several people talk at once, a transcript can get messy fast. Our new Nemotron 3 Diarization model tracks who spoke when, even when voices overlap. It handles up to eight speakers, has 100M parameters, and is now available on @huggingface 🤗 Your browser does not support the video tag. 🔗 View on Twitter 💬 6 🔄 5 ❤️ 31 👀 2653 📊 11 ⚡
