EAT_code
EAT_code copied to clipboard
yuangan
Official code for ICCV 2023 paper: "Efficient Emotional Adaptation for Audio-Driven Talking-Head Generation".
Hi, Could you kindly provide more details on the **_setting for model fine-tuning with CLIP_** and the **_zero-shot text-guided expression editing procedure_**? For model fine-tuning with CLIP, my understanding is...
作者你好，非常感谢你优秀的工作，我在使用./ckpt/qvt_img_pca_sync_4_01_11_304.pth.tar对第二阶段进行训练的时候，出现了“No discriminator in the state-dict. Dicriminator will be randomly initialized load optimizer_a2kp failed, train it from scratch”的错误，但是我观察代码，在第一阶段训练的时候是有optimizer_a2kp 的pre-trained checkpoint的，为什么会出现这样的警告？请问是我的预训练检查点设置有问题吗？
Thanks for the authors wonder work. As I am attempting to train the model myself and reproce the results, I would be grateful if the authors could give me more...
According to the instructions provided here: Note 2: To test with a custom audio, you need to replace the video_name/video_name.wav and deepspeech feature video_name/deepfeature32/video_name.npy. The output length will depend on...
I wonder how long does it take to train? And what hardware devices you use? Thank you! @yuangan
作者您好，我想对A2ET模型的训练进行复现，但是vox2数据集太大，预处理时间会很长，现在我这里有对vox2数据裁剪过的img和提取的对应的wav音频，请问能否完成对A2ET模型两种损失方式的训练？
 你好，我想用自己的数据集训练一下你的代码，现在数据集已经处理好了，但还存在几个问题需要请教一下， 1、如果用自己的数据集，这个tar文件可以直接下载使用吗还是要替换成自己数据集的权重文件，如果替换成自己的数据集的，怎么生成呢 2、这个voxselect文件要怎么替换呢
