Huge thanks to the original authors of SyncNet for this awesome codebase!

We use SyncNet as a standard evaluation metric for Talking Character Generation models.

To support broader adoption and easier integration into modern pipelines, we're actively maintaining and modernizing this classic implementation.

👉 Check out the updated version here: MoChaBench

If you find our work helpful, please consider citing both the original SyncNet and MoCha in your research. Your support means a lot!

The implementation follows a Hugging Face Diffusers-style structure.
We provided a
SyncNetPipeline Class, located at eval-lipsync\script\syncnet_pipeline.py.

You can initialize SyncNetPipeline by providing the weights and configs:

pipe = SyncNetPipeline(
 {
 "s3fd_weights": "path to sfd_face.pth",
 "syncnet_weights": "path to syncnet_v2.model",
 },
 device="cuda", # or "cpu"
)

The pipeline offers an inference function to score a single pair of video and speech. For fair comparison, the input speech should be a denoised vocal source extracted from your audio. You can use seperator like Kim_Vocal_2 for general noise remvoal and Demucs_mdx_extra for music removal

av_off, sync_confs, sync_dists, best_conf, min_dist, s3fd_json, has_face = pipe.inference(
 video_path="path to video.mp4", # RGB video
 audio_path="path to speech.wav", # speech track (must be denoised from audio, ffmpeg-readable format)
 cache_dir= "path to store intermediate output", # optional; omit to auto-cleanup intermediates
)