← Monday, October 5, 2026Models & trainingRelease

Transformers 5.18.0 adds streaming Nemotron 3 diarization

github.com 19 min read Editor score 7/10

The release adds Nemotron 3 Diarization, which supports streaming and offline inference, up to eight speakers, configurable latency buffers, and chunked audio without a maximum duration. These capabilities matter for engineers building real-time or long-form audio pipelines.

What

Transformers 5.18.0 adds Nemotron 3 Diarization, an open-weight streaming speaker diarization model that determines who spoke when.

How

It supports streaming and offline inference, up to eight speakers, configurable latency profiles, and chunked inference without a maximum audio duration.

Why it matters

Configurable buffers and chunked inference give engineers options for balancing latency and processing long audio streams.

Read on github.com →

Headline, summary, brief and diagram are written by a model from the source's own text; the link, byline and numbers come from the source. Read the original before relying on a claim.