From: Georgi Gerganov <redacted>
Date: Thu, 2 Nov 2023 13:28:48 +0000 (+0200)
Subject: talk-llama : add an up-to-date demo video
X-Git-Tag: upstream/1.7.4~1294
X-Git-Url: https://git.djapps.eu/?a=commitdiff_plain;h=74de25158e9eddc489e2bdf9abbcfd232a052962;p=pkg%2Fggml%2Fsources%2Fwhisper.cpp

talk-llama : add an up-to-date demo video
---

diff --git a/examples/talk-llama/README.md b/examples/talk-llama/README.md
index 545d725c..f073536c 100644
--- a/examples/talk-llama/README.md
+++ b/examples/talk-llama/README.md
@@ -4,6 +4,10 @@ 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
+
 ## Building
 
 The `talk-llama` tool depends on SDL2 library to capture audio from the microphone. You can build it like this: