Skip to content
Agientry
← Back to Videos

Nemotron 3.5 Transcribe: One Model for Multilingual Audio

Loading video
Loading video

NVIDIA Nemotron 3.5 Transcribe is an open-weight 30B MoE model with about 4B active parameters for 40-language transcription, speaker attribution, translation, and contextual prompting.

NVIDIANemotronSpeech RecognitionMultilingual ASRSpeaker DiarizationAudio Understanding
Category: research
Author: @NVIDIAAI
Date: 2026-10-28T00:00:00
Duration: 120.036s
Source: https://x.com/NVIDIAAI/status/2115462300241141882

Related Videos

JEV-Speech: Same 24-Layer Encoder, 2.18x Faster Inference
0:10

JEV-Speech: Same 24-Layer Encoder, 2.18x Faster Inference

@nrol_ling · 643 views · 2026-09-22
Speech RecognitionInference Optimization
RoboRender: Turning Simulated Trajectories into Photorealistic Video for Policy Training
2:02

RoboRender: Turning Simulated Trajectories into Photorealistic Video for Policy Training

@RavenHuang4 · 674 views · 2026-10-08
Sim-to-RealVideo Generation
Long-WAM: Scaling World-Action Model Context to 19.2s in Real Time
2:38

Long-WAM: Scaling World-Action Model Context to 19.2s in Real Time

@AaronWeiHuang · 483 views · 2026-10-08
World-action modelsVLA
DyaPlex: Full-Duplex Human-Robot Interaction at NeurIPS 2026
0:42

DyaPlex: Full-Duplex Human-Robot Interaction at NeurIPS 2026

@luminohope · 438 views · 2026-10-07
Human-robot interactionNeurIPS
interfaze-1-lite: Open-Weight Model for Deterministic Work
1:55

interfaze-1-lite: Open-Weight Model for Deterministic Work

@interfaze_ai · 387 views · 2026-10-05
OCRSpeech Recognition
Isaac Lab-Arena 0.3: Scale Robot Policy Evaluation in Simulation
0:14

Isaac Lab-Arena 0.3: Scale Robot Policy Evaluation in Simulation

@NVIDIARobotics · 773 views · 2026-09-15
Robotics SimulationPolicy Evaluation

As an Amazon Associate, we earn from qualifying purchases.