switching between trained models from the webui in standalone mode

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

686 stars 71 forks source link

switching between trained models from the webui in standalone mode #231

Closed Mixomo closed 2 months ago

Mixomo commented 2 months ago

Is your feature request related to a problem? Please describe.

No.

Describe the solution you'd like

The possibility to switch between different trained & fine-tuned models from the webui interface. That you can unload and load in VRAM those models, without the need to manually replace the xtts base model directory with the trained models each time you start webui.

Describe alternatives you've considered

Additional context

erew123 commented 2 months ago

Hi @Mixomo

This is all working in version 2 which is in development. Please see here for more details https://github.com/erew123/alltalk_tts/discussions/211

Thanks