-
-
Notifications
You must be signed in to change notification settings - Fork 128
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Request to Continue Updating AllTalk V1 #384
Comments
I am mostly focussing on v2 (when I get a chance). Im sure you will have caught my statement here on this You should be able to update V1's version of the TTS engine to 0.24.2 with this method (I cant think of any issues it would raise):
Swap the coqui-tts and tts to reverse the procedure if needed. As for Pytorch versions and such, thats a much more drawn out process that requires 1-2 days of validation on both Windows and Linux, along with building new DeepSpeed wheel files. Someone has done a PR for updating to later versions of Pytorch, though because of the reason I mention above in my statement, I have not had time to look at this, re-validate it all and there is still the need to build DeepSpeed wheel files. The PR is here #307 Thanks |
Thanks! Im going to close this ticket off for now. |
I understand that your focus has shifted to developing AllTalk V2, currently in beta. However, as a user who relies heavily on AllTalk V1 for XTTS, I kindly request that you continue updating V1, including the Coqui engine to version 0.24.2, until V2 reaches a stable release or becomes modular. This would greatly benefit those who solely use AllTalk for XTTS.
The text was updated successfully, but these errors were encountered: