(A fork of) a multi-voice TTS system trained with an emphasis on quality

Go to file

mrq a9de016230 added storing the loaded model's hash to the TTS object instead of relying on jerryrig injecting it (although I still have to for the weirdos who refuse to update the right way), added a parameter when loading voices to load a latent tagged with a model's hash so latents are per-model now		2023-03-02 00:44:42 +00:00
config
convert
scripts
tortoise	added storing the loaded model's hash to the TTS object instead of relying on jerryrig injecting it (although I still have to for the weirdos who refuse to update the right way), added a parameter when loading voices to load a latent tagged with a model's hash so latents are per-model now	2023-03-02 00:44:42 +00:00
voices
.gitignore
CITATION.cff
LICENSE
list_devices.py
main.py
MANIFEST.in
README.md
requirements_legacy.txt
requirements.txt
setup-cuda.bat
setup-cuda.sh
setup-directml.bat
setup-rocm.sh
setup.py
start.bat
start.sh
tortoise_tts.ipynb
update-force.bat
update-force.sh
update.bat
update.sh
webui.py

(QoL improvements for) TorToiSe

This repo is for my modifications to neonbjb/tortoise-tts.

Please migrate to mrq/ai-voice-cloning for future additions.