syncnet_python (907c0b57) conforms video to 25 fps and audio to 16 kHz mono before analysis, reports an integer frame offset (vshift minus argmin of averaged distances) with confidence = median minus minimum, so pipeline offsets are in 25 fps frames (40 ms) regardless of source frame rate; code...

syncnet_python (907c0b57) conforms video to 25 fps and audio to 16 kHz mono before analysis, reports an integer frame offset (vshift minus argmin of averaged distances) with confidence = median minus minimum, so pipeline offsets are in 25 fps frames (40 ms) regardless of source frame rate; code is MIT while the VGG page offers the model "for research purposes under Creative Commons Attribution License". Curator qualifications: Weights terms ambiguous: a research-purposes phrase attached to a CC BY link; no licence file with the weights; treat commercial use as unresolved. Default search range (+/-15 vs paper +/-1 s), offset sign interpretation, paper accuracy figures and LSE-D/LSE-C reuse (F2-F7) not reinspected. Training data (VoxCeleb2/LRS mentioned on page) rights separate and unknown. Static reading only; no model downloaded, no video or audio processed. Rights/verification notes are shown as limitations (L00 0019/ADR-0011): they restrict reuse of the cited material or record what was not verified; they are not cleared by this summary. Limitations: Static reading only; no model downloaded, no video or audio processed. [component_reuse_restriction] Eligible as unit/conform observation with weights hold; any offset correction recipe must divide by 25 for pipeline output. Evidence status: statements located in the cited sources by a correlated desk review (Claude); not executed; not independently reviewed.

{
  "citations": [
    {
      "url": "https://github.com/joonson/syncnet_python",
      "note": "run_pipeline.py lines 31, 267, 279 at 907c0b57; SyncNetInstance.py lines 21-25, 138-148; LICENSE.md; VGG lipsync page"
    }
  ]
}