From 44e962d1e2b6445481d71a56a5e41c083e5a7533 Mon Sep 17 00:00:00 2001 From: David Olowomeye <100958002+greatdaveo@users.noreply.github.com> Date: Sat, 20 Sep 2025 08:51:47 +0100 Subject: [PATCH] Created option for text viewer by adding BUZZ_PARAGRAPH_SPLIT_TIME environment variable (#1246) Co-authored-by: Raivis Dejus --- buzz/transcriber/file_transcriber.py | 4 +++- .../transcription_viewer/transcription_viewer_widget.py | 5 ++++- docs/docs/preferences.md | 1 + 3 files changed, 8 insertions(+), 2 deletions(-) diff --git a/buzz/transcriber/file_transcriber.py b/buzz/transcriber/file_transcriber.py index 34c4429a..87f2d636 100755 --- a/buzz/transcriber/file_transcriber.py +++ b/buzz/transcriber/file_transcriber.py @@ -166,8 +166,10 @@ def write_output( combined_text = "" previous_end_time = None + paragraph_split_time = int(os.getenv("BUZZ_PARAGRAPH_SPLIT_TIME", "2000")) + for segment in segments: - if previous_end_time is not None and (segment.start - previous_end_time) >= 2000: + if previous_end_time is not None and (segment.start - previous_end_time) >= paragraph_split_time: combined_text += "\n\n" combined_text += getattr(segment, segment_key).strip() + " " previous_end_time = segment.end diff --git a/buzz/widgets/transcription_viewer/transcription_viewer_widget.py b/buzz/widgets/transcription_viewer/transcription_viewer_widget.py index 763decfa..d0934407 100644 --- a/buzz/widgets/transcription_viewer/transcription_viewer_widget.py +++ b/buzz/widgets/transcription_viewer/transcription_viewer_widget.py @@ -1,3 +1,4 @@ +import os import logging from typing import Optional from uuid import UUID @@ -825,8 +826,10 @@ class TranscriptionViewerWidget(QWidget): combined_text = "" previous_end_time = None + paragraph_split_time = int(os.getenv("BUZZ_PARAGRAPH_SPLIT_TIME", "2000")) + for segment in segments: - if previous_end_time is not None and (segment.start_time - previous_end_time) >= 2000: + if previous_end_time is not None and (segment.start_time - previous_end_time) >= paragraph_split_time: combined_text += "\n\n" combined_text += segment.text.strip() + " " previous_end_time = segment.end_time diff --git a/docs/docs/preferences.md b/docs/docs/preferences.md index 730d3733..9ef6dfb1 100644 --- a/docs/docs/preferences.md +++ b/docs/docs/preferences.md @@ -119,3 +119,4 @@ Example of data collected by telemetry: ``` Buzz: 1.3.0, locale: ('lv_LV', 'UTF-8'), system: Linux, release: 6.14.0-27-generic, machine: x86_64, version: #27~24.04.1-Ubuntu SMP PREEMPT_DYNAMIC Tue Jul 22 17:38:49 UTC 2, ``` +**BUZZ_PARAGRAPH_SPLIT_TIME** - Time in milliseconds of silence to split paragraphs in transcript and add two newlines when exporting the transcripts as text. Default is `2000` or 2 seconds. Available since `1.3.0` \ No newline at end of file