Skip to content
This repository has been archived by the owner on Dec 9, 2024. It is now read-only.

Commit

Permalink
Update journal_jayden.md
Browse files Browse the repository at this point in the history
  • Loading branch information
jaydenstokes authored Jun 11, 2024
1 parent a7936ad commit 29f336b
Showing 1 changed file with 17 additions and 0 deletions.
17 changes: 17 additions & 0 deletions journals/journal_jayden.md
Original file line number Diff line number Diff line change
Expand Up @@ -28,3 +28,20 @@ This week I went over the code to get a more in-depth understanding of it and I
### Other
This week I experimented with different AI models to use (llama3, codellama and llava) to extract and format code from the video.
I created a test script to extract formatted code, an explanation of the formatted code and the timestamp of the code.

# Week 18
### Mark all that applied this week
- [x] Attended class
- [ ] Responded to PRs/Issues
- [x] Met with the team online. Discord
- [x] Committed to group repo

### Other
This week I implemented my experimental preprocess script into the OcrRoo program under the features/preprocessing-and-timestamps branch, as well as added multiple settings that change the behaviour of the preprocessing.
Some of the features this introduced are the following:
1. Preprocessing Videos
2. Enable / Disable Preprocessing
3. Toggle on/off formatted code and code explanations
4. Setting to change the preprocessing interval
5. Setting to change the llama endpoint (incase the user isn't locally hosting it, or is using a different port)
6. Timestamps detected to contain working code that appear below the media player whilst the video is processing. Once clicked, the video will go to that timestamp (planning to make this a lot nicer, didn't get to do that just yet though)

0 comments on commit 29f336b

Please sign in to comment.