search

MRzzm / DINet

The source code of "DINet: deformation inpainting network for realistic face visually dubbing on high resolution video."
895 stars 167 forks source link

Inference results in no audio sound, _add_audio.mp4 is not generated #103

Open Fortogether opened 2 months ago

Fortogether commented 2 months ago

My reasoning currently only saves _facial_dubbing.mp4 and _synthetic_face.mp4, however there is no _add_audio.mp4 file. The output video files are now without sound, how can I change my code or is this a problem with my environment?

tailangjun commented 2 months ago

应该是最后一步音视频合成失败了，你把 inference.py最后一步的脚本在 shell上执行一遍，看看提示啥报错 ffmpeg -i {} -i {} -c:v copy -c:a aac -strict experimental -map 0:v:0 -map 1:a:0 {}

Fortogether commented 2 months ago

ffmpeg存在动态库缺失，环境确实有些问题，我目前暂时用moviepy进行合成了