Wav2Lip
Wav2Lip copied to clipboard
Rudrabha
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.
when I run the project in the colab, i will show the error below: Using cuda for inference. Reading video frames... Number of frames available for inference: 223 Traceback (most...
Hey, model load is stuck, I have already update librosa to the 0.8.0 version and modify the funciton librosa.filters.mel in line 100 by altering "hp.sample_rate, hp.n_fft" to "sr=hp.sample_rate, n_fft= hp.n_fft"....
Colab Notebook example cannot be run error message: `Using cuda for inference. Reading video frames... Number of frames available for inference: 210 Traceback (most recent call last): File "/content/Wav2Lip/inference.py", line...
i use 16k mono ,6.7025s wav , mel 167 frame->167 *40 ms=6.68s the same ,i use 6s wav , mel 147 5.58s why? issue:audio also play , the mel have...
Number of frames available for inference: 373 Traceback (most recent call last): File "inference.py", line 280, in main() File "inference.py", line 225, in main mel = audio.melspectrogram(wav) File "/root/W字幕君交流场所Lip/audio.py", line...
how can i get 128x128 resolution output 如何获得128x128尺寸的虚拟数字人？ can anyone provides me with ideas and suggestions? thank in advance. 大家能提供给我一些思路和方法么，非常感谢。
Hi! I am trying to train the model using LRS2 dataset. The steps I followed are 1. Download the dataset 2. Concatenate the files 3. Extract it to the directory...
Videos that include constant talking audio and shots of person speaking and person not speaking have a problem. When person in the video is not speaking, lip is trying to...
Hi, I am working with AMD Radeon gpu and I am unable to use the GPU acceleration when running the solution locally. It looks like there is an AMD configuration...
