Not established from the available sources.
NVIDIA · MODEL RELEASE TRACKER
NVIDIA Nemotron ASR Streaming
A streaming automatic speech recognition (ASR) model variant from NVIDIA. It is included in NVIDIA's DIN Deploy open-source C++ samples and was measured to achieve about 39× real-time GPU acceleration on DGX Spark when run via ONNX Runtime with the NVIDIA TensorRT RTX execution provider.CURRENT SNAPSHOT3/5 DIMENSIONS WITH DATA
The dimensions that change the decision.
Not established from the available sources.
ModalitySpeech / audio.
Measured GPU accelerationReported GPU acceleration of about 39× real-time on DGX Spark when run through the DIN Deploy samples.
Availability in samplesIncluded in the open-source DIN Deploy C++ samples, which export Hugging Face checkpoints to ONNX and run inference via ONNX Runtime with the NVIDIA TensorRT RTX execution provider (Windows and Linux).
VERIFIABLE FACTS
Every value stays attached to a source and date.
CAPABILITIES · Primary taskDEVELOPER CLAIM
Automatic speech recognition (ASR).
MODALITIES · ModalityDEVELOPER CLAIM
Speech / audio.
BENCHMARKS · Measured GPU accelerationDEVELOPER CLAIM
Reported GPU acceleration of about 39× real-time on DGX Spark when run through the DIN Deploy samples.
AVAILABILITY · Availability in samplesDEVELOPER CLAIM
Included in the open-source DIN Deploy C++ samples, which export Hugging Face checkpoints to ONNX and run inference via ONNX Runtime with the NVIDIA TensorRT RTX execution provider (Windows and Linux).
WHAT CHANGED