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

TTS Vocoder Waveglow 88M

Model

WaveGlow Speech Synthesis model with 88M Parameters

TTS Vocoder Waveglow 268M

Model

WaveGlow Speech Synthesis model with 268M Parameters

TTS Vocoder Uniglow

Model

UniGlow Speech Synthesis model

TTS Vocoder Squeezewave

Model

SqueezeWave Speech Synthesis model

TTS Vocoder Melgan

Model

MelGAN Speech Synthesis model

TTS Vocoder Hifigan

Model

HiFiGAN Speech Synthesis model

TTS En TalkNet

Model

Speech Synthesis model trained on female English speech

TTS En Tacotron2

Model

Tacotron2 Speech Synthesis model trained on female English speech

TTS En LJ UnivNet

Model

UnivNet speech synthesis model trained on female English speech (LJSpeech dataset)

TTS En LJ Mixer-TTS-X

Model

Mixer-TTS Speech Synthesis model trained on female English speech (LJSpeech dataset)

TTS En LJ Mixer-TTS

Model

Mixer-TTS Speech Synthesis model trained on female English speech (LJSpeech dataset)

TTS En LJ HiFi-GAN

Model

HiFiGAN Speech Synthesis model trained female English speech (LJSpeech dataset)

TTS En LibriTTS UnivNet

Model

UnivNet speech synthesis model trained on English speech (LibriTTS dataset)

TTS En Glowtts

Model

Glowtts Speech Synthesis model trained on female English speech

TTS En FastSpeech 2

Model

FastSpeech 2 speech synthesis model trained on female English speech

TTS En FastPitch

Model

FastPitch Speech Synthesis model trained on female English speech

TTS En E2E FastPitch Hifigan

Model

FastPitch+HiFiGAN End-to-End Speech Synthesis model trained on female English speech

TTS En E2E Fastspeech2 Hifigan

Model

FastSpeech2+HiFiGAN End-to-End Speech Synthesis model trained on female English speech

TTS De FastPitch HiFi-GAN

Model

This collection contains two models: 1) FastPitch (around 50M parameters) trained on OpenSLR neutral German dataset with over 23 hours of German speech and 1 speaker. 2) HiFi-GAN trained on mel spectrograms produced by the FastPitch model in (1).

TTS DE Multi-Speaker FastPitch HiFiGAN

Model

This collection includes two German models: FastPitch trained on the HUI-Audio-Corpus-German clean dataset where the 5-largest amount of speakers are selected and balanced; HiFiGAN is trained on mel-spectrograms predicted by the Multi-speaker FastPitch.

RIVA EnglishUS Hifigan

Model

RIVA EnglishUS Fastpitch

Model

Riva Marblenet Voice Activity Detection

Model

Riva Marblenet Voice Activity Detection

STT Kab Conformer-Transducer Large

Model

Conformer-Transducer-Large model for Kabyle Automatic Speech Recognition, trained on Mozilla Common Voice 10.0 Kabyle train set.

Riva ASR Spanish Inverse Normalization Grammar

Model

Base Spanish grammar