-
-
这个有没有人详细讲下怎么解决的啊
-
我看到作者有尝试deepspeech_pb_path="/disk4/keyu/DeepSpeech/deepspeech-0.9.2-models.pbmm"，请问这个模型能加载成功吗？我这边加载是会报错的
-
我使用OpenFace FeatureExtraction得到xxx.xcv文件后，rename为au.xcv，训练时会报错KeyError: ' AU45_r'
![Uploading 截屏2023-12-23 17.56.04.png…]()
-
Hello! I want to express my appreciation for your excellent work.
I have a question regarding inference speed.
I recently conducted a test using a 14-second-long audio clip (equivalent to 351 fr…
-
the result is showed below: (is there any key parameters to set and make it stable)
https://github.com/KU-CVLAB/GaussianTalker/assets/95479496/304de436-6fbe-4aab-8c68-c8eaa34b432f
-
处理前人脸：
处理后人脸：
:
File "/home/tailangjun/Documents/AIGenHuman/NerfLips/DFRF/data_util/deepspeech_features/extract_ds_features.py", …
-
通过几个月的训练，踩过不少坑，终于把整个流程都走通了，下面是中文推理效果
https://github.com/MRzzm/DINet/assets/12316965/548c3f93-b14f-44c9-819a-f27d8b142c94
目前还存在几个大问题，这里做一下总结
1. 生成区域抖动严重
2. 生成区域色差问题
3. 生成区域边框裁剪