talk-llama : move up-to-date demo to top (#1417)

This commit is contained in:
Asad Memon 2023-11-02 09:50:13 -07:00 committed by GitHub
parent 74de25158e
commit d445098c8f
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23

View File

@ -2,12 +2,14 @@
Talk with an LLaMA AI in your terminal
[Demo Talk](https://user-images.githubusercontent.com/1991296/228024237-848f998c-c334-46a6-bef8-3271590da83b.mp4)
*Latest perf as of 2 Nov 2023 using Whisper Medium + LLaMA v2 13B Q8_0 on M2 Ultra:*
https://github.com/ggerganov/whisper.cpp/assets/1991296/d97a3788-bf2a-4756-9a43-60c6b391649e
*Previous demo running on CPUs*
[Demo Talk](https://user-images.githubusercontent.com/1991296/228024237-848f998c-c334-46a6-bef8-3271590da83b.mp4)
## Building
The `talk-llama` tool depends on SDL2 library to capture audio from the microphone. You can build it like this: