From a4f3119ba6fb1a3b68155bd61c501d66a884f5dd Mon Sep 17 00:00:00 2001
From: Mr-Neutr0n <64578610+Mr-Neutr0n@users.noreply.github.com>
Date: Wed, 11 Feb 2026 19:34:54 +0530
Subject: [PATCH] Fix double application of audio/video offset for concatenated
 segments

In clip(), the start and end variables already include start_ost and
end_ost offsets after the clamping step, but the data slice for
subsequent segments was applying the offsets a second time via
data[start+start_ost*16:end+end_ost*16]. Use data[start:end] instead.

Similarly in video_clip(), the time_acc_ost calculation was adding the
offsets again even though start and end already incorporated them.
Use (end - start) directly since the duration already reflects the
offset-adjusted boundaries.

Fixes #129
Fixes #144
---
 funclip/videoclipper.py | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/funclip/videoclipper.py b/funclip/videoclipper.py
index 3873a2d..f94adb9 100644
--- a/funclip/videoclipper.py
+++ b/funclip/videoclipper.py
@@ -128,7 +128,7 @@ def clip(self, dest_text, start_ost, end_ost, state, dest_spk=None, output_dir=N
                 start = min(max(0, start+start_ost*16), len(data))
                 end = min(max(0, end+end_ost*16), len(data))
                 start_end_info += ", from {} to {}".format(start, end)
-                res_audio = np.concatenate([res_audio, data[start+start_ost*16:end+end_ost*16]], -1)
+                res_audio = np.concatenate([res_audio, data[start:end]], -1)
                 srt_clip, _, srt_index = generate_srt_clip(sentences, start/16000.0, end/16000.0, begin_index=srt_index-1)
                 clip_srt += srt_clip
         if len(ts):
@@ -238,7 +238,7 @@ def video_clip(self,
                 subtitles = SubtitlesClip(subs, generator)
                 video_clip = CompositeVideoClip([video_clip, subtitles.set_pos(('center','bottom'))])
             concate_clip = [video_clip]
-            time_acc_ost += end+end_ost/1000.0 - (start+start_ost/1000.0)
+            time_acc_ost += end - start
             for _ts in ts[1:]:
                 start, end = _ts[0] / 16000, _ts[1] / 16000
                 srt_clip, subs, srt_index = generate_srt_clip(sentences, start, end, begin_index=srt_index-1, time_acc_ost=time_acc_ost)
@@ -258,7 +258,7 @@ def video_clip(self,
                     _video_clip = CompositeVideoClip([_video_clip, subtitles.set_pos(('center','bottom'))])
                     # _video_clip.write_videofile("debug.mp4", audio_codec="aac")
                 concate_clip.append(copy.copy(_video_clip))
-                time_acc_ost += end+end_ost/1000.0 - (start+start_ost/1000.0)
+                time_acc_ost += end - start
             message = "{} periods found in the audio: ".format(len(ts)) + start_end_info
             logging.warning("Concating...")
             if len(concate_clip) > 1: