Looking for some support / guide (paid)

[rurounijones]

Ahoi all.

I am looking for someone to help me get setup on Coqui since I have been banging my head against trying to get it working for a long time.

Current state:

• I have spoken voice lines in wav format with associated text (This data has been successfully used to train Azure Cognitive Services Speech Recognition)
• I have a WSL2 VM running on windows that detects my nVidia GTX 1080 graphics card. (The Coqui docker image never worked for me as it never detected the graphics card. If you are confident you can get that working then go ahead)

Basically I want someone who can run me through everything to get from the above to a trained model, bootstrapped from an English coqui checkpoint, on my local machine. Using a cloud service is not an option (e.g. no Google Colab or similar). This includes steps such as the kenlm scorer etc. I last attempted this half a year ago so may need to do some updating of things.

How I see this working is basically sitting on a voice channel with a remote desktop application talking, watching, and learning how it is done. More details here: https://gitlab.com/overlordbot/srs-bot/-/issues/48

If anyone is interested then please contact me here or by email (In profile)