Wav2Lip
Wav2Lip copied to clipboard
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.
First of all, thank you very much for your great paper and code sharing. While working on my paper, I would like to measure the metric presented in the paper...
I am trying to train Wav2lip+GAN from scratch(LRS2 train) with the instruction you have provided. Even after 100 epoch Sync loss(Evaluation ) was 1.2. So, I have manually changed Sync...
I followed the README.md operation in the evaluation and placed an mp4 file in the folder syncnet_python \ data \ root. conda activate syncnet sh calculate_scores_real_videos.sh ./data/root When I am...
FAKE:100
Hello, I have a question for you. When I was training, the loss of Fake became bigger and bigger, and finally it rose to 100, and the loss of percep...
Hi @prajwalkr, After checking the code released. I have an issue that: In [wav2lip_train.py:L92:](https://github.com/Rudrabha/Wav2Lip/blob/master/wav2lip_train.py#L92) ```python def get_segmented_mels(self, spec, start_frame): ............ for i in range(start_frame_num, start_frame_num + syncnet_T): m = self.crop_audio_window(spec,...
Hi, I have experimenting with the code, but regardless of what I try with the expert lip-sync discriminator, the loss does not seem to go below 0.68. I am using...
请问有人按照官方提供步骤的从0开始训练CMLR数据集吗,本人训练前没有过滤数据集,最终训练出来的视频和音频完全对应不上,是因为没有过滤数据集的原因吗,或者有人过滤完数据集训练成功了吗,可以+V交流,最好也是学生
i made one great video i was really pleased with, and then the second time i tried to run wav2lip i've been getting the same error over and over....it happens...
服务器运算用户等待时间和成本有点扛不住,想看看能不能有类似轻量级算法或者方案,在客户端来实现。 谢谢各位高手。