Skip to main content
ContainersNVIDIADeepSeek-R1NVIDIALlama-3.1-Nemotron-70B-InstructNVIDIAPyTorch
CollectionsNVIDIAOmniverse Kit (FB)NVIDIADeepStream SDKNVIDIAOmniverse Kit App Streaming
ModelsNVIDIAStyleGAN3 pretrained modelsNVIDIAPeopleNetNVIDIATrafficCamNet
ResourcesNVIDIARiva Skills Quick Start
Helm ChartsNVIDIAGPU OperatorNVIDIANVIDIA NIM Operator

Search

Search thousands of GPU-optimized Containers, pretrained Models, SDKs, and Helm charts—ready to accelerate AI, digital twins, and HPC from cloud to edge.
Accelerate custom generative AI app deployment using pre-built containers with optimized AI models.

Displaying 99 results

PyNvVideoCodec
NVIDIA
PyNVVideoCodec (Python NVIDIA Video Codec) is a set of python APIs for hardware accelerated video decoding and encoding.
Resource
Riva ASR English(en-GB) LM
NVIDIA
Base English 3-gram LM
Model
Omniverse Maya Connector
NVIDIA
The Omniverse Maya Connector provides USD file format import and export support for Nucleus servers and MDL materials translation.
Resource
usd-exporter-revit
NVIDIA
The USD to Revit Exporter enables USD export and MDL material support.
Resource
RIVA Conformer ASR English - ASR set 6.0
NVIDIA
English Conformer ASR model trained on ASR set 6.0
Model
NemoCurator Prompt Task and Complexity Classifier
NVIDIA
A multi-headed classification model to classify English text prompts across task types and complexity dimensions.
Model
Omniverse Unreal Connector
NVIDIA
The Omniverse Unreal Connector enables USD import and export support for your 3D workflows on Nucleus servers and MDL materials translation.
Resource
SyntheticaDETR
NVIDIA
SytheticaDETR is a real-time object detection model based on a transformer architecture trained entirely in simulation and works on real images zero-shot.
Model
RIVA Conformer ASR English(en-US)
NVIDIA
English Conformer ASR model for en-US
Model
Omniverse 3ds Max Connector
NVIDIA
Installer for the Omniverse 3ds Max Connector, enabling USD workflows with Nucleus servers and MDL materials.
Resource
Speech Synthesis English FastPitch
NVIDIA
Mel-Spectrogram prediction conditioned on input text with LJSpeech voice.
Model
Aerial CUDA-Accelerated RAN
NVIDIA
An SDK (Software Development Kit) for building commercial-grade, AI-native, 3GPP, and O-RAN compliant 5G/6G gNB software on NVIDIA-accelerated computing platforms.
Resource
Omniverse Unity Connector
NVIDIA
The Omniverse Unity Connector enables users to import and export USD files for their workflows with Nucleus servers and provides translation of MDL materials.
Resource
Speech to Text English Citrinet
NVIDIA
Speech to Text Citrinet models for English.
Model
RIVA Punctuation and Capitalization for English
NVIDIA
For each word in the input text, the model: 1) predicts a punctuation mark that should follow the word (if any), the model supports commas, periods and question marks) and 2) predicts if the word should be capitalized or not.
Model
RIVA Citrinet ASR English en-US
NVIDIA
English en-US Citrinet ASR model trained on RIVA ASR set
Model
Nova Orin
NVIDIA
Collection of resources for Nova Orin.
Resource
Omniverse ParaView Connector
NVIDIA
The Omniverse ParaView Connector enables the USD Export file format and supports MDL materials.
Resource
Omniverse Creo Connector
NVIDIA
The Omniverse Creo Connector enables OpenUSD Export support to Nucleus servers and provides MDL material support.
Resource
storage-api
NVIDIA
OpenAPI and gRPC specifications for the Omniverse USD Storage API.
Resource
STT En FastConformer Hybrid Transducer-CTC Large Streaming 80ms
NVIDIA
This collection contains the large version (114M) of the streaming speech recognition model trained on NeMo ASRSET for English with look-ahead of 80ms. All models are cache-aware hybrid FastConformer with both Transducer and CTC decoders.
Model
STT Multilingual FastConformer Hybrid Transducer-CTC Large P&C
NVIDIA
The large version (114M) of the Multilingual speech recognition model with a FastConformer encoder and a Hybrid decoder (joint RNNT-CTC loss). The model has a vocab size of 2560 and emits text with punctuation and capitalization.
Model
TitaNet-S
NVIDIA
TitaNet Small model for Speaker Verification and Diarization tasks
Model
Aerial Omniverse DT Sim Source
NVIDIA
This is the source code for the Aerial Omniverse Digital Twin. It comes with the build environment necessary to create custom docker runtime images.
Resource
1-24 of 99 items

Modal Content

NVIDIA uses cookies to improve your experience on our web site. We and our third-party partners also use cookies and other tools to collect and record information you provide as well as information about your interactions with our websites for performance improvement, analytics, and to assist in marketing efforts. By clicking "Accept All", you consent to our use of cookies and other tools as described in our Cookie Policy. You can manage your cookie settings by clicking on "Manage Settings." By continuing to use this site or by clicking one of the buttons below, you agree to our Terms of Service (which contains important waivers). Please see our Privacy Policy for more information on our privacy practices.

Manage Settings