syncnet-python
https://github.com/nawta/SyncNet_py309_313

This repository contains code under two licenses.

1. MIT License (see LICENSE)
   The original SyncNet code by Joon Son Chung
   (https://github.com/joonson/syncnet_python) and the code written for
   this repository: syncnet_python/__init__.py, syncnet_python/cli.py,
   syncnet_python/safe_syncnet_utils.py,
   syncnet_python/test_error_handling.py,
   syncnet_python/test_lse_metrics.py, and the syncnet/, scripts/ and
   config/ folders.

2. Apache License 2.0 (see LICENSE-APACHE)
   The following files come from MoChaBench
   (https://github.com/congwei1230/MoChaBench, folder eval-lipsync/script/),
   which is distributed under the Apache License 2.0. MoChaBench's LICENSE
   file does not name a copyright holder; the files are credited here to
   the MoChaBench authors. MoChaBench's versions are in turn based on the
   original SyncNet code above. All files in this list except
   syncnet_pipeline.py are unchanged copies of MoChaBench's files.

     syncnet_python/syncnet_pipeline.py   (modified by nawta; the file
                                           header lists the changes)
     syncnet_python/SyncNetInstance.py
     syncnet_python/SyncNetModel.py
     syncnet_python/detectors/__init__.py
     syncnet_python/detectors/s3fd/__init__.py
     syncnet_python/detectors/s3fd/box_utils.py
     syncnet_python/detectors/s3fd/nets.py
     syncnet_python/run_syncnet_pipeline_on_1example.py
     syncnet_python/run_syncnet_pipeline_on_mocha_generation_on_mocha_bench.py
     syncnet_python/run_syncnet_pipeline_on_your_own_model_results.py

Model weights

   weights/syncnet_v2.model and weights/sfd_face.pth are copies of the files
   published by the Visual Geometry Group, University of Oxford, at
   https://www.robots.ox.ac.uk/~vgg/software/lipsync/. That page states:
   "The model can be used for research purposes under Creative Commons
   Attribution License." Neither the MIT License nor the Apache License 2.0
   above applies to these files.
