sangramsingnk/Speech

Text-to-Speech Recipe Users can create speech signals from an input text by using text-to-speech (TTS), also referred to as speech synthesis. Popular TTS and Vocoder models, such as Tacotron 2, are supported by SpeechBrain (e.g, HiFIGAN).

语言：Jupyter Notebook · GitHub 星标：19 · Fork：6

在 GitHub 上查看原仓库