# Variational Autoencoder

This is a KL16 variational autoencoder (VAE) model trained on the ImageNet-1k dataset for image-to-image conversion tasks.

Swaram is an advanced Malayalam speech synthesis model capable of generating high-quality speech waveforms from input text.

A Malagasy text-to-speech model developed by Facebook, part of the Massively Multilingual Speech project

Chichewa text-to-speech model developed by Meta AI, based on VITS architecture, supporting high-quality speech synthesis

A Tigrinya text-to-speech model developed by Meta, based on the VITS architecture, supporting high-quality speech synthesis

Fon text-to-speech model developed by Meta, based on the VITS architecture, supporting the conversion of Fon text into natural speech

A Waray-Waray text-to-speech model developed by Meta, based on the VITS architecture, supporting high-quality speech synthesis

English text-to-speech model developed by Meta, based on the VITS architecture, supporting high-quality speech synthesis

BiMeanVAE is a model based on Variational Autoencoder (VAE), primarily used for text summarization tasks.