Current Python Version : 3.11.7 Current CUDA Version : CUDA is not available

[CRCODE22]

(K:\text-generation-webui\installer_files\env) K:\text-generation-webui>start_windows.bat 15:54:37-963446 INFO Starting Text generation web UI 15:54:37-967443 WARNING You are potentially exposing the web UI to the entire internet without any access password. You can create one with the "--gradio-auth" flag like this:

                     --gradio-auth username:password

                     Make sure to replace username:password with your own.

15:54:37-970444 INFO Loading settings from "settings.yaml" 15:54:37-980444 INFO Loading the extension "alltalktts" [AllTalk Startup] _ __ [AllTalk Startup] / \ | | | | | | | _ | | / | [AllTalk Startup] / \ | | | | |/ ` | | |/ / | | | | _ \ [AllTalk Startup] / | | | | | (| | | < | | | | ) | [AllTalk Startup] // __|| ||\,|||_\ || |_| |/ [AllTalk Startup] [AllTalk Startup] Config file check : No Updates required [AllTalk Startup] AllTalk startup Mode : Text-Gen-webui mode [AllTalk Startup] WAV file deletion : Disabled [AllTalk Startup] DeepSpeed version : 0.11.2+unknown [AllTalk Startup] Model is available : Checking [AllTalk Startup] Model is available : Checked [AllTalk Startup] Current Python Version : 3.11.7 [AllTalk Startup] Current PyTorch Version: 2.2.1+cpu [AllTalk Startup] Current CUDA Version : CUDA is not available [AllTalk Startup] Current TTS Version : 0.22.0 [AllTalk Startup] Current TTS Version is : Up to date [AllTalk Startup] AllTalk Github updated : 12th May 2024 at 13:00 [AllTalk Startup] TTS Subprocess : Starting up [AllTalk Startup] [AllTalk Startup] AllTalk Settings & Documentation: http://127.0.0.1:7851 [AllTalk Startup] [AllTalk Model] XTTSv2 Local Loading xttsv2_2.0.2 into cpu [AllTalk Startup] Warning TTS Subprocess has NOT started up yet, Will keep trying for 120 seconds maximum. Please wait. [AllTalk Model] Coqui Public Model License [AllTalk Model] https://coqui.ai/cpml.txt [AllTalk Model] Model Loaded in 13.44 seconds. [AllTalk Model] Ready

The standalone version works without problems CUDA Deepspeed everything works

The problem is the extension with text generation webui there CUDA does not work.

I have an NVIDIA GeForce RTX 4060 Ti 16GB

OS Windows 11 Using CMD

I have installed CUDA versions: v11.7 v11.8 v12.1 v12.3

[erew123]

Hi @CRCODE22

If you are using the TGWUI environment (as above) you will still need to install the AllTalk requirements into that environment, but your PyTorch on that version doesnt have CUDA installed.

As per my instruction on the other ticket (But this is specifically for TGWUI)

1) Start the TGWUI environment with cmd_windows.bat in the TGWUI directory 2) pip cache purge (to wipe clean the pip cache as it wont download a full copy of Pytorch otherwise) 3) pip uninstall torch torchaudio torchvision (remove old torch without cuda) 4) Then run:

pip install torch==2.2.1+cu121 torchaudio>=2.2.1+cu121 torchvision --upgrade --force-reinst all --extra-index-url https://download.pytorch.org/whl/cu121

Thanks

[erew123]

The other way to do this and go back to factory fresh, is to delete the installer_files folder in TGWUI folder:

Then run start_windows.bat in the TGWUI folder:

When asked, say you have an Nvidia GPU, and answer N (this selects it installing Pytorch with CUDA):

Once that is all run through, it will have built your custom TGWUI Python environment with PyTorch with CUDA. You will need to close the console and then run through the standard AllTalk setup process:

https://github.com/erew123/alltalk_tts?tab=readme-ov-file#-quick-setup-text-generation-webui--standalone-installation

or as shown in the video here:

https://www.youtube.com/watch?v=icn2XS5rUH8

Thanks