StarGANv2-VC: A Diverse, Unsupervised, Non-parallel Framework for Natural-Sounding Voice Conversion

Improved Nano Syntax Highlighting Files

A minimalist Jekyll theme for running a blog or publication powered by Jekyll and GitHub Pages

VITS: Conditional Variational Autoencoder with Adversarial Learning for End-to-End Text-to-Speech

MelGAN vocoder (compatible with NVIDIA/tacotron2)

Implementation of "Learning Latent Representations for Style Control and Transfer in End-to-end Speech Synthesis"

eSpeak NG is an open source speech synthesizer that supports more than hundred languages and accents.

MELD: A Multimodal Multi-Party Dataset for Emotion Recognition in Conversation

🤖 💬 Deep learning for Text to Speech (Discussion forum: https://discourse.mozilla.org/c/tts)

A collection of useful scripts, templates, and examples for clusters using SLURM https://slurm.schedmd.com/