Nvidia releases open Nemotron 3.5 Transcribe speech model
Nvidia says the 30-billion-parameter model keeps about 4 billion active and tops open-weight English ASR models.
58
AI model
Nemotron 3 Diarization
- Mentions · 7d0
- Mentions · 30d1
- All mentions3
- First seenSep 23, 2026
- Last mentioned14d ago
Timeline
3 articles · newest firstNvidia drops a free 100M-parameter model that identifies up to eight speakers in real time
Nvidia released free 100-million-parameter Nemotron 3 Diarization, which labels up to eight speakers in real time.
45
NVIDIA Releases Nemotron 3 Diarization: A 100M-Parameter Open-Weight Model That Tracks 8 Speakers in Real Time
NVIDIA released Nemotron 3 Diarization, a 100M open-weight model tracking up to eight overlapping speakers.
54
Appears with
- Nvidiavendor · 3
- Streaming Sortformerai model · 2
- Nvidiaorganization · 2
- Hugging Faceorganization · 2
- Nemotron 3 Diarizationproduct · 1
- David AIorganization · 1
- Nemotron 3.5 Transcribeai model · 1
- Nemotron 3 Nano Omniai model · 1
- NeMoproduct · 1
- Artificial Analysisorganization · 1
- Voxtral Smallai model · 1
- Parakeet TDT 0.6B v3ai model · 1
- Parakeetai model · 1
- Granary v2product · 1
- Parakeetproduct · 1
- Voxtral 3ai model · 1
Entities are extracted by the model from each article. First seen , last mentioned . Watching keeps it in this browser only (no account); the watchlist page and dashboard alerts use it.