Evaluation results are different from the paper

[jyeongho]

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 to compare my work with wav2lip results.

Using the method presented in evaluation folder, I generated videos from lrs2 and lrs3 test dataset and measured LSE-D LSE-C metrics. However, the results were different from those presented in the paper.

My result for lrs2:

	LSE-D	LSE-C
Wav2Lip	7.15	6.77
Wav2Lip + GAN	7.21	6.79

My result for lrs3:

	LSE-D	LSE-C
Wav2Lip	7.00	7.15
Wav2Lip + GAN	7.10	7.07

I did the same method as suggested, and this result came out. Is the code in the evaluation the one you used to extract results in the paper?