AI Models - Computer Vision, Conversational AI, and More

Welcome Guest

Many AI applications have common needs: classification, object detection, language translation, text-to-speech, recommender engines, sentiment analysis, and more. When developing applications with these capabilities, it is much faster to start with a model that is pre-trained and then tune it for a specific use case. The NGC catalog offers pre-trained models for a variety of common AI tasks that are optimized for NVIDIA Tensor Core GPUs, and can be easily re-trained by updating just a few layers, saving valuable time.

Sort: Last Modified

STT En Conformer-CTC Large

Model

Conformer-CTC-Large model for English Automatic Speech Recognition, Trained on NeMo ASRSET

STT En Conformer-CTC Medium

Model

Conformer-CTC-Medium model for English Automatic Speech Recognition, Trained on NeMo ASRSET

STT En Conformer-CTC Small

Model

Conformer-CTC-Small model for English Automatic Speech Recognition, Trained on NeMo ASRSET

STT En Conformer-Transducer Large

Model

Conformer-Transducer-Large model for English Automatic Speech Recognition, Trained on NeMo ASRSET

STT En Conformer-Transducer Small

Model

Conformer-Transducer-Small model for English Automatic Speech Recognition, Trained on NeMo ASRSET

STT En Conformer-Transducer Medium

Model

Conformer-Transducer-Medium model for English Automatic Speech Recognition, Trained on NeMo ASRSET

STT En Conformer-CTC Large LibriSpeech

Model

Conformer-CTC-Large model for English Automatic Speech Recognition, Trained with NeMo on LibriSpeech dataset

STT En Conformer-CTC Medium LibriSpeech

Model

Conformer-CTC-Medium model for English Automatic Speech Recognition, Trained with NeMo on LibriSpeech dataset

STT En Conformer-CTC Small LibriSpeech

Model

Conformer-CTC-Small model for English Automatic Speech Recognition, Trained with NeMo on LibriSpeech dataset

Riva ASR English LM

Model

Base English n-gram LM trained on LibriSpeech, Switchboard and Fisher

nnUNet PyTorch checkpoint 2D AMP

Model

nnUNet2d PyTorch checkpoint trained with AMP on fold 2

EfficientNet-B0 backbone savedmodel (TensorFlow2, AMP, Imagenet)

Model

EfficientNet-B0 TensorFlow2 savedmodel without prediction heads

nnUNet PyTorch checkpoint 3D AMP

Model

nnUNet3d PyTorch checkpoint trained with AMP on fold 2

UNet_Medical TensorFlow2 TF-TRT model (AMP)

Model

UNet_Medical TensorFlow2 TF-TRT model trained with AMP

UNet_Medical TensorFlow2 checkpoint (AMP)

Model

UNet_Medical TensorFlow2 checkpoint trained with AMP

UNet_Medical TensorFlow2 SavedModel (AMP)

Model

UNet_Medical TensorFlow2 SavedModel trained with AMP

Wide & Deep TF checkpoint (Base, 128k, v1, AMP)

Model

Wide & Deep Base TensorFlow checkpoint trained with AMP

Waveglow PyTorch checkpoint (AMP, 256ch)

Model

Waveglow PyTorch checkpoint with 256-channel WN base trained with AMP

UNet_Industrial TensorFlow checkpoint (AMP)

Model

UNet_Industrial TensorFlow checkpoint trained with AMP

Transformer-XL Base TensorFlow checkpoint (AMP, Base)

Model

Transformer-XL Base Base TensorFlow checkpoint trained with AMP

Tacotron2 TorchScript model (AMP)

Model

Tacotron2 TorchScript model trained with AMP

Tacotron2 PyTorch checkpoint (AMP)

Model

Tacotron2 PyTorch checkpoint trained with AMP

SSD TensorFlow checkpoint (FP32)

Model

SSD TensorFlow checkpoint trained with FP32

SSD TensorFlow checkpoint (AMP)

Model

SSD TensorFlow checkpoint trained with AMP

SSD PyTorch checkpoint (AMP)

Model

SSD PyTorch checkpoint trained with AMP