Nemotron-3-Diarization-preview
nvidia/Nemotron-3-Diarization-preview
رسمي · BF16 · nemo
اجرا چاپېریال تایید شوی: NeMo
| Precision / quantization | بڼه | بټونه | پر خپروونکي باور | د ځایپرځای کولو حالت |
|---|---|---|---|---|
| BF16 | nemo | 16 | رسمي | اجرا چاپېریال تایید شوی |
NVIDIA Nemotron · د ویناوالو پېژندنه · Nemotron 3
Nemotron 3 Diarization Preview: مشخصات، د GPU اړتیاوې او جواز
Nemotron 3 Diarization Preview is NVIDIA’s 100M-parameter speaker-diarization model for identifying who spoke when in streaming or recorded audio.
ټول پارامېټرونه۱۰۰M
فعال پارامېټرونهDense ماډل
د context کړکۍN/A / نېغه پرتله نه شي کېدای
د نسخې وضعیتمخکتنه · وروستی
معماريStreaming Sortformer Transformer
موداليټيګانېغږ
جوازother
د ځایپرځای کولو حالتله تخنیکي پلوه د ارزونې لپاره چلېدای شي
سوداګریز وضعیتناڅرګند / د سپارښتنې وړ نه دی
د خپرېدو نېټه2026-08-27
تخنیکي پېژندڅېره
| برخه | ارزښت |
|---|---|
| Purpose | Speaker diarization: identify who spoke when |
| Speaker capacity | Up to 8 speakers, ordered by arrival |
| Inference modes | Streaming and offline |
| Input | 16 kHz mono WAV, FLAC, OPUS or MP3 |
| Output | [T, 8] speaker activity probabilities |
| Input buffer | 80 ms to 30.4 s; chunked inference has no fixed duration limit |
| د اجرا چاپېریال | NVIDIA NeMo with PyTorch |
| Precision | BF16 |
| Reference hardware | NVIDIA Blackwell RTX PRO 5000 |
معماري، پیاوړتیاوې او کارونې
This gated, self-hostable preview belongs to the Nemotron Audio/Speech domain and Speaker Diarization track. It accepts 16 kHz mono audio and returns activity probabilities for as many as eight speakers ordered by arrival.
The 100M-parameter model uses a 31-layer Streaming Sortformer Transformer with rotary position embeddingونه. Ten-millisecond Mel frames are downsampled to 80 ms encoder frames, then a Conv1D stage produces speaker activity probabilities.
Streaming and offline diarization
Up to eight arrival-ordered speakers
Official NeMo checkpoint with BF16 evidence
Evaluation of meeting and call speaker segmentation
Streaming speaker-change analysis
Offline diarization research on recorded audio
تایید شوي checkpoint-ونه او quantization-ونه
یوازې د سرچینې له خوا تصدیق شوې کره بڼې چې له دې نسخې سره تړلې دي، ښودل کېږي.
سپارښتل شوی هارډوېیر
Use the exact gated .nemo checkpoint through NVIDIA NeMo with the documented PyTorch backend and BF16 precision. The NVIDIA reference measurement used an RTX PRO 5000 Blackwell GPU; this is test hardware, not a commercial کوربهتوب offer.
ناڅرګند / د سپارښتنې وړ نه دی
سوداګریز حقونه نه دي تایید شوي، نو د دې خپرونې سوداګریزه سپارښتنه نه کېږي.
د جواز او خپل کوربهتوب ملاحظات
Access requires acceptance of NVIDIA’s evaluation license. Input must be 16 kHz mono audio; chunked inference supports long recordings, while the buffer can be configured from 80 ms to 30.4 seconds.
The NVIDIA permits internal testing and evaluation only. It prohibits production use and commercial کوربهتوب, and restricts use to NVIDIA GPU systems. Consult the official terms for the complete obligations.
ناڅرګند / د سپارښتنې وړ نه دی. سوداګریز حقونه نه دي تایید شوي، نو د دې خپرونې سوداګریزه سپارښتنه نه کېږي.
د نسخو مهالوېش
nvidia/nemotron/nemotron-3-diarization-preview
د سرچینې جزئیات
د سرچینې revision: a43022e40b9883fb75078c47c5d4c995436863bb26e26f13a1a7e836ea519229
ډېرې پوښتل شوې پوښتنې
What does Nemotron 3 Diarization Preview do?
It identifies speaker activity over time and assigns activity probabilities to as many as eight speakers in arrival order.
Can it process live and recorded audio?
Yes. NVIDIA documents both streaming and offline inference through the NeMo checkpoint.
Can it be used for commercial production?
No commercial offer is shown. The verified NVIDIA license limits this release to internal testing and evaluation and prohibits production use.
رسمي مراجع
وروستی تایید: 2026-09-03