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.

Go to file

Henri Rantanen c645589b88 Merge pull request #3 from eternalliving/RemoteEngine Created Remote engine for Glados TTS		2022-03-21 21:58:14 +02:00
models	Initial commit	2022-02-16 11:39:20 -08:00
utils	Fixing all my mistakes :)	2022-03-20 07:41:03 -07:00
.gitignore	Updated TTS Engine to be in single script	2022-03-20 04:14:36 -07:00
README.md	fixed readme error	2022-03-20 07:44:36 -07:00
engine.py	Fixed cache arrangement and all my other errors	2022-03-20 09:03:04 -07:00
glados.py	Added comments	2022-03-12 18:28:25 +02:00

README.md

GLaDOS Text-to-speech (TTS) Voice Generator

Neural network based TTS Engine.

If you want to just play around with the TTS, this works as stand-alone.

python3 glados-tts/glados.py

the TTS Engine can also be used remotely on a machine more powerful then the Pi to process in house TTS: (executed from glados-tts directory

python3 engine-remote.py

Default port is 8124 Be sure to update settings.env variable in your main Glados-voice-assistant directory:

TTS_ENGINE_API			= http://192.168.1.3:8124/synthesize/

Description

The initial, regular Tacotron model was trained first on LJSpeech, and then on a heavily modified version of the Ellen McClain dataset (all non-Portal 2 voice lines removed, punctuation added).

The Forward Tacotron model was only trained on about 600 voice lines.
The HiFiGAN model was generated through transfer learning from the sample.
All models have been optimized and quantized.