A GLaDOS TTS, using Forward Tacotron and HiFiGAN. Inference is fast and stable, even on the CPU. A low quality vocoder model is included for mobile use. Rudimentary TTS script included. Works perfectly on Linux, partially on Maybe someone smarter than me can make a GUI.
To follow up on https://github.com/R2D2FISH/glados-tts/issues/14 I added a script to download the models using github releases. However I admit I added quite a lot of "unrelated niceties" which I don't mind removing if you don't want them.
To follow up on https://github.com/R2D2FISH/glados-tts/issues/14 I added a script to download the models using github releases. However I admit I added quite a lot of "unrelated niceties" which I don't mind removing if you don't want them.
Some things to note: