From d3cfee1eb3cd598390f5cb180db75ec89e06066f Mon Sep 17 00:00:00 2001 From: Doug Ware Date: Tue, 30 Jul 2024 16:03:12 -0400 Subject: [PATCH] AntArmyIntro --- docs/Journal/TranscriptionAndDiarization.html | 2 +- docs/Projects/AntArmyPreview.html | 98 +++++++++++++++++++ docs/Projects/toc.html | 3 + docs/Projects/toc.json | 2 +- docs/manifest.json | 35 +++++-- docs/sitemap.xml | 72 +++++++------- docs/toc.html | 2 +- docs/toc.json | 2 +- docs/video/AntArmyIntro.mp4 | 3 + 9 files changed, 173 insertions(+), 46 deletions(-) create mode 100644 docs/Projects/AntArmyPreview.html create mode 100644 docs/video/AntArmyIntro.mp4 diff --git a/docs/Journal/TranscriptionAndDiarization.html b/docs/Journal/TranscriptionAndDiarization.html index c344b03..4b8f71d 100644 --- a/docs/Journal/TranscriptionAndDiarization.html +++ b/docs/Journal/TranscriptionAndDiarization.html @@ -119,7 +119,7 @@

Who said w [SPEAKER_00] : [(00:00:31.980, 00:00:36.160)] : I'm going to hand off to my good friend Jeremy Thake, and he's going to walk you through the first half of this session. Thanks, Barno. I appreciate it. And thank you for coming to Build. [SPEAKER_01] : [(00:00:37.960, 00:00:40.280)] : So I'm Jeremy Thake. I'm a

Identify speaker names using phi-3-medium

-

Often at this point I have to do some manual steps to replace “SPEAKER_00” with a real name because I find that very often, perhaps most of the time, people don’t say their own names or refer to others by name. But still, if I am doing this process, I intend to use the transcript with a language model to get insight from the content.

In this case, Barnam and Jeremy demonstrated excellent presenter skills and the text contains their names. Thanks to this, I can use a language model to extract their names and update the transcript. For this task I used microsoft/Phi-3-medium-4k-instruct-onnx-directml which is a version of Phi-3-medium-4k-instruct optimized for use with ONNX runtime which makes it super fast on my RTX-4090 GPU. Use it if you have a GPU and are using Windows.

+

Often at this point I have to do some manual steps to replace “SPEAKER_00” with a real name because I find that very often, perhaps most of the time, people don’t say their own names or refer to others by name. But still, if I am doing this process, I intend to use the transcript with a language model to get insight from the content.

In this case, Barnam and Jeremy demonstrated excellent presenter skills and the text contains their names. Thanks to this, I can use a language model to extract their names and update the transcript – an perfect example of using a language model to get insight from the content!

For this task I used microsoft/Phi-3-medium-4k-instruct-onnx-directml which is a version of Phi-3-medium-4k-instruct optimized for use with ONNX runtime which makes it super fast on my RTX-4090 GPU. Use it if you have a GPU and are using Windows.

My notebook contains code to pull out a few lines before and after a speaker’s first appearance and build a prompt:

 # Create the prompt with the current speaker and their context  
         prompt = f"""  
diff --git a/docs/Projects/AntArmyPreview.html b/docs/Projects/AntArmyPreview.html
new file mode 100644
index 0000000..6ad99bc
--- /dev/null
+++ b/docs/Projects/AntArmyPreview.html
@@ -0,0 +1,98 @@
+
+
+  
+    
+      AntArmy – Together we are strong! 
+      
+      
+      
+      
+      
+      
+      
+      
+      
+      
+      
+
+      
+
+      
+      
+  
+
+  
+    
+ +
+ +
+
+
+
+
Table of Contents
+ +
+
+ +
+
+
+ +
+
+ + + +
+ +
+

AntArmy – Together we are strong!

+ +
+
+ +
+
+ + + +
+ +
+ +
+
+ + + + + \ No newline at end of file diff --git a/docs/Projects/toc.html b/docs/Projects/toc.html index bb53526..79ec7b0 100644 --- a/docs/Projects/toc.html +++ b/docs/Projects/toc.html @@ -12,6 +12,9 @@