Rudrabha / Wav2Lip

This repository contains the codes of "A Lip Sync Expert Is All You Need for Speech to Lip Generation In the Wild", published at ACM Multimedia 2020. For HD commercial model, please try out Sync Labs
https://synclabs.so
10.28k stars 2.21k forks source link

Reading video frames... ^C error #267

Closed bmox closed 3 years ago

bmox commented 3 years ago

Using cuda for inference. Reading video frames... ^C !cd Wav2Lip && python inference.py --checkpoint_path checkpoints/wav2lip_gan.pth --face "../sample_data/input_vid.mp4" --audio "../sample_data/input_audio.wav" I follow every step and also install requirements.txt. input video.mp4 and input audio.wav duration is 7 minutes.

What is the problem ?

Rudrabha commented 3 years ago

^C is a key-board interrupt in general that the user provides to stop the execution of a program. Can you elaborate on this issue further?

bmox commented 3 years ago

I'm running the code on google colab. The video and audio is 7-10 minutes long and the video size is 25-30mb. Face is available in every frame. FPS is 24. file type .mp4 resolution 1920*1080 , audio type is .wav. But when I use a small video and audio it work.

Rudrabha commented 3 years ago

I am not sure why this issue is coming. Please try it on a local machine, maybe. The other workaround is to chunk the audio and video into short segments and then sync them. You can rejoin them again later. I believe this issue is specific to collab since we have exported videos for up to 15 minutes without facing any issue.