A lot of bug fixes and edge cases

audio/audio_utils.py

@@ -20,7 +20,7 @@ def extract_audio_segment_file(video: Path, start_time: float, end_time: float,
     which makes the operation fast and preserves the original audio quality.
 
     Args:
-        video: Path to the source video file.
+        German_Videout_mkv: Path to the source video file.
         start_time: Start time of the audio segment (seconds or FFmpeg time format).
         end_time: End time of the audio segment.
         out_audio: Path to the output audio file.

main.py

@@ -223,12 +223,7 @@ def process_one(German_Video: Path, Quality_Video: Path, output_dir: Path, offse
 
 
 def main():
-    # Configure these paths for your own legally owned media.
+    output_dir = "/home/honney/mount/Media/tmp/serien/ready/Classroom of the Elite/Season 01"
-    # Placeholders below: first dir holds the dubbed (e.g. German) source,
-    # second dir holds the high-quality video source.
-    output_dir = "./output_dir"
-    dubbed_dir = "./dubbed_source/Season 01"
-    quality_dir = "./high_quality/S01"
     if not os.path.isdir(output_dir):
         raise NotADirectoryError(f"Output directory is not a valid Directory: {output_dir}")
     start_num = 2
@@ -241,12 +236,12 @@ def main():
     for i in tqdm(episodes, desc="Episodes"):
     # i =1
     # if i:
-        german_pattern = f"{dubbed_dir}/Example Series S01E{i:02}.mkv"
+        german_pattern = f"/home/honney/mount/Media/tmp/serien/ger_low_quality/Classroom of the Elite (2017-2024) [imdbid-tt7263328]/Season 01/Classroom of the Elite S01E0{i:02}.mkv"
         if os.path.isfile(german_pattern):
             German_Video = [german_pattern]
         else: 
             German_Video = glob.glob(german_pattern)
-        quality_pattern = f"{quality_dir}/E{i:02}*"
+        quality_pattern = f"/home/honney/mount/Media/tmp/serien/high_quality/Classroom of the Elite/S01/E{i:02}*"
         if os.path.isfile(quality_pattern):
             Quality_Video = [quality_pattern]
         else: 

mkv/chapter.py

@@ -10,7 +10,8 @@ from typing import Tuple, List
 import json
 
 def get_chapters(file: Path) -> List[Tuple[float, float]]:
-    """Return list of (start_time, duration) for each chapter."""
+    """Return list of (start_ti
+from .intro_outro importme, duration) for each chapter."""
     cmd = [
         "ffprobe",
         "-i", str(file),
@@ -65,5 +66,5 @@ def get_intro_outro(file: Path, length: float = 90.0) -> List[Tuple[float, float
 ### https://github.com/jonbarrow/open-anime-timestamps?utm_source=chatgpt.com
 
 if __name__ == '__main__':
-    file = "./output_dir/episode.mkv"
+    file = "/home/honney/projects/mkv/output_dir/08.mkv"
     print(get_intro_outro(Path(file)))

readme.md

@@ -1,176 +1 @@
-# anime_dub_sync
+This script needs ffmpeg and mkvtoolkit/mkvtoolnix installed to work
-
-Transfer a dubbed audio track (e.g. German) from a low-quality source file onto a
-high-quality video file, with automatic A/V offset detection and verification.
-
-Only use this with sources you legally own. All paths and titles in this repo
-are generic placeholders — do not commit real media filenames, absolute local
-paths, or release-group names.
-
-## Requirements
-
-System tools (must be on `PATH`):
-
-- `ffmpeg` + `ffprobe`
-- `mkvmerge` (from MKVToolNix)
-
-Python (>= 3.10):
-
-- `opencv-python`, `scipy`, `numpy`, `soundfile`, `tqdn`
-- see `requirements.txt`
-
-Install:
-
-```bash
-pip install -r requirements.txt
-```
-
-## Repository layout
-
-```text
-main.py                  # batch + single-episode orchestration
-utils.py                 # subprocess helper
-audio/
-  __init__.py
-  audio_utils.py         # ffmpeg extraction, concat, shifting, mux helpers
-  audio_cross_correlation.py  # intro/outro audio offset measurement
-video/
-  __init__.py
-  video_utils.py         # ffprobe wrapper
-  scene_change_cross_correlation.py  # primary video offset detection
-  temporal_cross_correlation.py      # alternative/legacy motion-signal method
-mkv/
-  __init__.py
-  chapter.py             # chapter parsing, intro/outro candidate search
-  intro_outro.py         # final sync verification
-  check_intro_outro.py   # CLI wrapper for verification
-```
-
-## How it works
-
-### 1. Video offset detection (`video/`)
-
-`video/scene_change_cross_correlation.py:70` — `corelate_videos(vid1, vid2, fps)`:
-
-1. `get_scene_change_signal` decodes each video with OpenCV at 160x90 grayscale,
-   computes `mean(diff^2)` per frame. Cuts produce large spikes.
-2. `resample_signal` resamples both signals to a common FPS with
-   `scipy.signal.resample`.
-3. Both signals are z-normalized, then `scipy.signal.correlate(mode='full')`
-   finds the lag with peak correlation.
-4. Lag in samples / FPS = offset in seconds. Positive means `vid1` starts
-   after `vid2`.
-
-`video/video_utils.py:14` — `probe_video(path)` returns
-`(fps, duration, codec, start_time)` via `ffprobe -show_streams -show_format`.
-
-`video/temporal_cross_correlation.py:52` — `find_temporal_offset` is a similar
-motion-signal correlator. It is exported but not used by `main.py`; the active
-path is `corelate_videos`.
-
-### 2. Audio splicing (`audio/`)
-
-`audio/audio_utils.py`:
-
-- `extract_audio_segment_file(video, start, end, out)` — extracts `0:a:0`
-  with ffmpeg to stereo AAC `.mka`.
-- `extract_audio_segment_tmp(file, (start, duration) | start, end, stream)` —
-  extracts a stream to a temp 44.1 kHz PCM WAV for analysis.
-- `get_audio_duration(file)` — parses `DURATION` tag via ffprobe.
-- `stick_together_audio(left, right, out)` — concatenates with the ffmpeg
-  concat demuxer (`-c copy`, no re-encode).
-- `add_silence(file, offset)` — `adelay` (offset > 0, silence at start) or
-  `apad` (offset < 0, silence at end), re-encoded to Opus.
-- `replace_with_shifted_mka(mkv, mka, audioline, offset)` — physically shifts
-  with `adelay` / `atrim+asetpts`, re-encodes to Opus 160k, replaces the track
-  with `mkvmerge`, tags it `ger` / `German (Opus Stereo)`.
-- `get_audio_streams`, `get_track_info`, `shift_audio` — stream enumeration
-  and in-place shift helpers.
-
-`audio/audio_cross_correlation.py:39` — `get_audio_offset(file1, file2, time)`:
-decodes to mono 44.1 kHz WAV, mean-normalizes, `scipy.signal.correlate`, returns
-lag / sample-rate in seconds.
-
-### 3. Intro/outro verification (`mkv/`)
-
-`mkv/chapter.py:12` — `get_chapters(file)` lists `(start, duration)` via
-`ffprobe -show_chapters`.
-
-`mkv/chapter.py:35` — `get_intro_outro(file, length=90.0)` keeps chapters with
-duration within `[length/2, length*2]`. Expects exactly 2 (intro + outro).
-
-`mkv/intro_outro.py:8` — `check_intro_outro_sync(file, length, uncertainty,
-max_offset)`:
-
-1. Trims `uncertainty` (default 10%) off each intro/outro edge.
-2. Extracts first and last audio streams for intro and outro.
-3. Audio-correlates intro pair and outro pair.
-4. Returns `(True, mean_offset, last_stream)` if
-   `|mean(outro_offsets) - mean(intro_offsets)| < max_offset` (default 0.1 s),
-   else `(False, None, None)`.
-
-### 4. Orchestration (`main.py`)
-
-`main.py:18` — `mux_audio_into_output()` runs `mkvmerge` to add the synced
-`.mka` as a German track.
-
-`main.py:37` — `process_one(German_Video, Quality_Video, output_dir,
-offset=None)` runs 9 `tqdm` steps:
-
-1. `Probe video` — probe both inputs.
-2. `Compute offset` — `corelate_videos`, or use supplied `offset`.
-3. `Extract pre beginning` — head of quality audio before dub starts
-   (skipped if < 0.05 s).
-4. `Extract german audio` — main dubbed segment.
-5. `Extract post end` — tail of quality audio (skipped if < 0.5 s,
-   appended only if > `MIN_END_DUR = 2.5` s).
-6. `Combine audio` — concat head + dub + tail; falls back to `add_silence`.
-7. `Mux` — mkvmerge into `output_dir/<quality_stem>.mkv`.
-8. `Cleanup` — removes temp `_original_audio*.mka`.
-9. `Final check` — `check_intro_outro_sync`; sub-frame residual is fixed with
-   `replace_with_shifted_mka` if `|offset| > 1/fps`. Failures are renamed to
-   `[FAILED]_*.mkv`, chapterless files to `[NO CHAPTER]_*.mkv`.
-
-## Usage
-
-Single episode (output dir as 3rd arg, else `../output_dir`):
-
-```bash
-python main.py <dubbed_source.mkv> <high_quality_source.mkv> [output_dir]
-python main.py dubbed_ep01.mkv quality_ep01.mkv ./output_dir
-```
-
-With explicit offset in seconds (bypass video correlation), pass it as 4th
-argument handling inside `process_one` — currently CLI uses auto-detect; edit
-or call the function directly for manual offsets.
-
-Batch: edit `main()` in `main.py:225` (`output_dir`, `dubbed_dir`,
-`quality_dir`, episode range), then:
-
-```bash
-python main.py
-```
-
-Verify an existing file without re-muxing:
-
-```bash
-python mkv/check_intro_outro.py ./output_dir/episode.mkv
-```
-
-## Configuration
-
-- `main.py:16` `MIN_END_DUR = 2.5` — minimum tail length to append.
-- `main.py:14` `DEBUG = False` — enable ffmpeg segment logging.
-- `mkv/intro_outro.py:8` `length=90.0, uncertainty=0.1, max_offset=0.1` —
-  expected OP/ED length and tolerances.
-
-## Notes and limitations
-
-- Needs chapter marks to run the final check; files without them are kept
-  with a `[NO CHAPTER]_` prefix and return `False`.
-- Scene-change correlation assumes both files are the same episode cut.
-  Different cuts, missing scenes, or very dark/flat video degrade the peak.
-- `utils.py:4` `run(cmd)` prints combined stdout on failure, then re-raises
-  `CalledProcessError`.
-- Do not commit `.mkv` / `.mka` media or absolute filesystem paths. Keep
-  `output_dir/` and temp audio out of git.

video/scene_change_cross_correlation.py

@@ -100,8 +100,8 @@ def corelate_videos(vid1: Path, vid2: Path, fps: float) -> float:
 
 # --- Example Usage ---
 if __name__ == "__main__":
-    video_path_1 = Path("./examples/high_quality_episode.mkv")
+    video_path_1 = Path("/home/honney/projects/mkv/Maid-sama/11_org.mkv")
-    video_path_2 = Path("./examples/dubbed_episode.mkv")
+    video_path_2 = Path("/home/honney/projects/mkv/Maid-sama/11_ger.mkv")
 
     target_fps, _, _, _ = probe_video(video_path_1)
 

video/temporal_cross_correlation.py

@@ -81,8 +81,8 @@ if __name__ == '__main__':
         offset_f, offset_t = find_temporal_offset(Path(sys.argv[1]), Path(sys.argv[2]))
         print(f"Offset between Videos:\n{offset_f} Frames\n{offset_t} s")
     elif len(sys.argv) == 1:
-        file1 = "./examples/high_quality_episode.mkv"
+        file1 = "/home/honney/projects/mkv/Maid-sama/11_org.mkv"
-        file2 = "./examples/dubbed_episode.mkv"
+        file2 = "/home/honney/projects/mkv/Maid-sama/11_ger.mkv"
         if not os.path.isfile(file1):
             raise ValueError(f"{file1} is not a valid file path")
         if not os.path.isfile(file2):