# Non-autoregressive TTS

The first neural speech synthesis model supporting multiple speakers and dialects, capable of generating high-quality emotional speech in four Catalan dialects

A text-to-speech model integrating FastSpeech2Conformer with HiFi-GAN, providing efficient and high-quality speech synthesis

FastSpeech2Conformer is a non-autoregressive text-to-speech (TTS) model that combines the advantages of FastSpeech2 and the Conformer architecture, enabling fast and efficient generation of high-quality speech from text.