nvidia/Nemotron-3-Diarization
voice-activity-detection model by nvidia
Older snapshot: check the original source for current information.
From the publisher
Model card & documentation
Source previewRead the publisher’s intended use, setup instructions, evaluations and limitations. The original model card is the source of truth.
Nemotron 3 Diarization is an open-weight speaker diarization model designed to determine "who spoke when" in real-world audio. It supports both streaming and offline inference and handles up to eight speakers. Following Sortformer [\[1\]](#ref-1), the model resolves speaker permutation by ordering its output channels according to each speaker's first arrival in the input audio. For streaming inference, the model adopts the Arrival-Order Speaker Cache (AOSC) and FIFO queue introduced in Streaming Sortformer [\[2\]](#ref-2). The AOSC retains speaker information from earlier chunks to preserve speaker identities over time, while the FIFO queue provides recent frame context for each processing step. A single checkpoint supports input buffer latency as low as 80 ms for latency-critical applications, although the lowest recommended configuration is 0.32 s; the offline-style configuration uses a 30.4 s input buffer. The output frame resolution is configurable in multiples of 10 ms. With chunked inference, the maximum audio duration is…
Read the full model card ↗ · Preview checked 2026-11-06T00:03:46.165Z
Inside the original model card — Document outline
- Nemotron 3 Diarization
- Description
- Release Date
- Live Action Demo Page
- What does max 8-speaker diarization mean ?
- How to use this model
- Run locally with NeMo-Speech.cpp
- NVIDIA NeMo Speech
- 🚀 Quick Start: Run Diarization Now
- Loading the Model
- Input Format
- Setting up Streaming Configuration
Headings are captured from the source. Links open the publisher’s document, not a locally hosted copy.
Links from the model card
References supplied by the publisher, not independently verified endorsements. Check the destination before downloading files or entering credentials.
Documentation belongs to its respective authors. Reported project/model license: openmdw-1.1. A listing is not a grant of reuse or training rights. Confirm the document’s own terms at the source.
Model overview
nvidia/Nemotron-3-Diarization is a voice-activity-detection model repository published by nvidia on Hugging Face. The source reports the nemo library.
This page summarizes Hub metadata. For intended use, training data, evaluation results and limitations, consult the original model card.
Model facts
- Task
- voice-activity-detection
- Library
- nemo
- Recent downloads (30 days)
- 77,153
- Cumulative likes
- 766
- Hugging Face trending score
- 55
- Reported safetensors parameters
- 99,226,504
- Architecture
- Nemotron3DiarizationForAudioFrameClassification
- License
- openmdw-1.1
- Access
- Not gated by Hugging Face
- Created
- 2026-09-01T13:16:57.000Z
- Last modified
- 2026-09-24T05:52:51.000Z
Compatibility and lineage
Language coverage was not reported.
Base-model lineage was not included.
Parameter count is not a RAM/VRAM requirement. Check precision, quantization, context length and runtime compatibility in the model card; no hardware or API-cost claim is inferred here.
Use and evaluate
Check license terms and access requirements first. Review the model card’s documented loading instructions, evaluations and safety limitations. Benchmark scores are not imported by this directory, and popularity is not an accuracy ranking.
No model weights are downloaded or executed by AltAPIs. Never enable remote model code without reviewing it.
Source and freshness
Source: Hugging Face Hub. Metadata observed 2026-10-13T06:40:58.146Z. Daily imports are snapshots, not real-time monitoring.
Popularity and source listings do not establish security, suitability, licensing rights or benchmark performance.