apunkt/SurfSense
1
0
Fork 0
mirror of https://github.com/MODSetter/SurfSense.git synced 2026-05-17 18:35:19 +02:00
Code Issues Projects Releases Packages Wiki Activity

Update transcript processing to use new API object attributes

Browse source
This commit is contained in:
sandeeppainuly 2025-09-28 12:09:17 +02:00
parent c08508c0c4
commit 7bb8e77ee1
1 changed files with 3 additions and 3 deletions
Download patch file Download diff file Expand all files Collapse all files

6
surfsense_backend/app/tasks/document_processors/youtube_processor.py
View file

@ -141,9 +141,9 @@ async def add_youtube_video_document(
# Include complete caption information with timestamps # Include complete caption information with timestamps
transcript_segments = [] transcript_segments = []
for line in captions: for line in captions:
start_time = line.get("start", 0) start_time = line.start
duration = line.get("duration", 0) duration = line.duration
text = line.get("text", "") text = line.text
timestamp = f"[{start_time:.2f}s-{start_time + duration:.2f}s]" timestamp = f"[{start_time:.2f}s-{start_time + duration:.2f}s]"
transcript_segments.append(f"{timestamp} {text}") transcript_segments.append(f"{timestamp} {text}")
transcript_text = "\n".join(transcript_segments) transcript_text = "\n".join(transcript_segments)