vits2 backbone with multilingual-bert
Towards Human-Sounding Speech
Bringing BERT into modernity via both architecture changes and scaling
🍦 Speech-AI-Forge is a project developed around TTS generation model, implementing an API Server and a Gradio-based WebUI.
GLM-TTS: Controllable & Emotion-Expressive Zero-shot TTS with Multi-Reward Reinforcement Learning