erew123 / alltalk_tts

AllTalk is based on the Coqui TTS engine, similar to the Coqui_tts extension for Text generation webUI, however supports a variety of advanced features, such as a settings page, low VRAM support, DeepSpeed, narrator, model finetuning, custom models, wav file maintenance. It can also be used with 3rd Party software via JSON calls.
GNU Affero General Public License v3.0
864 stars 98 forks source link

DeepSpeed N/A in Gradio Alltalk_v2 #322

Closed SuperMaximus1984 closed 2 weeks ago

SuperMaximus1984 commented 2 weeks ago

I've been using AllTalk_1.9c for a while with DeepSpeed enabled, but after I got V2 installed I see this in Gradio: image And CLI outputs as if everything is installed as it should: image

What can be wrong with DeepSpeed and other configuration functions that are N/A? Just in case - requirements.txt for Standalone installation are up-to-date, PyTorch either, as you may see.

erew123 commented 2 weeks ago

Hi @SuperMaximus1984 Features that are not available for a specific TTS engine will not be selectable.

image

On the engine information tab, you can find details of each TTS engines capabilities. Piper does not support DeepSpeed:

image

Xtts does:

image

Thanks