Skip to content

improve timestamp handling in transcripts #15

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
kroll-j wants to merge 1 commit into
base: main
Choose a base branch
from
Open

improve timestamp handling in transcripts #15

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 2 additions & 2 deletions prompt.txt
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -5,8 +5,8 @@ Your goal is to extract segments that have **Perfect Narrative Completeness** (S

### INPUT FORMAT EXPLAINED
The transcript below is a continuous text stream with embedded **Time Tags** like `(12s)`.
- Example: `"Hello world (0s). Today we are going to (3s) fly to the moon."`
- These tags represent the approximate timestamp of the *preceding* text.
- Example: `"(0s) Hello world. Today we are going to (3s) fly to the moon."`
- These tags represent the timestamp of the word following the tag.
- Use them to calculate duration. Duration = (End Tag - Start Tag).

### STRICT VIRAL RULES (The "ViralCutter Standard"):
Expand Down
7 changes: 3 additions & 4 deletions scripts/create_viral_segments.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -181,7 +181,7 @@ def preprocess_transcript_for_ai(segments):

# Try to start with (0s) based on first segment
first_start = segments[0].get('start', 0)
full_text += f"({int(first_start)}s) "
full_text += f"({first_start:.2f}s) "
last_tag_time = first_start

for seg in segments:
Expand All @@ -190,9 +190,8 @@ def preprocess_transcript_for_ai(segments):

full_text += text + " "

if end_time - last_tag_time >= 4:
full_text += f"({int(end_time)}s) "
last_tag_time = end_time
full_text += f"({int(end_time)}s) "
last_tag_time = end_time

return full_text.strip()

Expand Down