Smol TTS models are here! OuteTTS-0.1-350M ā Zero shot voice cloning, built on LLaMa architecture, CC-BY license! š„ Three-step approach to TTS: The model is extremely impressive for 350M parameters! Kudos to the @OuteAI team on such a brilliant feat ā Iād love to see this be applied on larger data and smarter backbones like [ā¦]
