LocalLLaMA

3 readers

1 users here now

Community to discuss about Llama, the family of large language models created by Meta AI.

founded 1 year ago

MODERATORS

communick@poweruser.forum

Step by step guide for local with voice? (alien.top)

submitted 11 months ago by DuckFormer@alien.top to c/localllama@poweruser.forum

3 comments fedilink hide all child comments

Hi,

I've tried to follow a couple step by step guides from August, but the models they've used are now apparently outdated, and when I try to load the model into obbaguba, I get a bunch of errors.

So I've downloaded the GGUF models from ThatBloke and still having issues with the models only good for "taking instructions" and the server crashes when I try use the chat feature..

Are there any step by step guides that someone can recommend? I want to set up a UI where I can text chat, and also talk to the AI and have the AI reply in voice mode...

System is 7950x3d with 4090 and 64GB DDR5..

I've set up Anaconda and python, also got stable diffusion working previously as well.. just not Llama2..

Cheers in advance

top 3 comments

sorted by: hot top controversial new old

[–] opi098514@alien.top 1 points 11 months ago

For anyone that is interested. Here is a code that will do this as long as you have some knowledge of python and conda you should maybe be able to get it to work. Just follow the instructions. Maybe.

https://github.com/opisaac9001/TTS-With-ooba-and-voice

[–] Evening_Ad6637@alien.top 1 points 11 months ago

I’ve tested „amica“ yesterday. I was very impressed. Try it out:

https://github.com/semperai/amica

[–] DuckFormer@alien.top 1 points 11 months ago

What code clips are people using for the TTS? Can you share the WAVs?