Speech Synthesis: WaveGlow Model Card

Model Overview

WaveGlow is a Glow-based (alternatively flow-based) model that generates audio conditioned on mel spectrograms. WaveGlow is a reversible neural network. It can be run in two modes: the first mode takes audio and transforms it to samples drawn from a normal distribution, and the second mode takes samples from a normal distribution and transforms it to audio. Both modes are conditioned on a mel spectrogram.

Intended Use

WaveGlow is intended to be used as the second part of a two stage speech synthesis pipeline. WaveGlow takes a mel spectrogram and returns audio.

Input Mel spectrogram of shape (batch x mel_channels x time)

Output Audio of shape (batch x time)

How to Use This Model

The provided .ejrvs checkpoint can be used, in junction with a Tacotron2 checkpoint, to generate speech via Jarvis. To deploy a TTS service via Jarvis, please refer to the Jarvis documentation

Training Information

This model is trained on LJSpeech sampled at 22050Hz, and can be used to generate most voices in most languages without retraining. We have observed this trained WaveGlow to generate English audio and Mandarin audio.

License

By downloading and using the models and resources packaged with TLT Conversational AI, you would be accepting the terms of the Jarvis license

Ethical AI

NVIDIA’s platforms and application frameworks enable developers to build a wide array of AI applications. Consider potential algorithmic bias when choosing or creating the models being deployed. Work with the model’s developer to ensure that it meets the requirements for the relevant industry and use case; that the necessary instruction and documentation are provided to understand error rates, confidence intervals, and results; and that the model is being used under the conditions and in the manner intended.

Citations and Further Reading

WaveGlow paper: https://arxiv.org/abs/1811.00002