Issues
- 2
wav2lip [mp3 @ 000002a6d5b45d80] Estimating duration from bitrate, this may be inaccurate
#683 opened by maic2209 - 1
filelists文件中的test.txt
#643 opened by guo-king666 - 0
出wav2lip高清通用模型256尺寸,包含推理代码,oonx加速推理。需要微信 tke365
#682 opened by wahaha2423 - 2
First step not working for me!
#677 opened by zwin55 - 3
> 应该是librosa版本的问题,但是老版本的安装上不上,我一直很苦恼怎么解决这个问题
#655 opened by hanhan-20240326 - 0
Traceback (most recent call last): File "inference.py", line 280, in <module> main() File "inference.py", line 250, in main total=int(np.ceil(float(len(mel_chunks))/batch_size)))): File "D:\lq\anaconda3\envs\wav2lip\lib\site-packages\tqdm\std.py", line 1127, in __iter__ for obj in iterable: File "inference.py", line 113, in datagen face_det_results = face_detect(frames) # BGR2RGB for CNN face detection File "inference.py", line 92, in face_detect raise ValueError('Face not detected! Ensure the video contains a face in all the frames.') ValueError: Face not detected! Ensure the video contains a face in all the frames.
#681 opened by wuye901126 - 0
Question abount get_segmented_mels
#680 opened by ainrichman - 0
- 1
- 4
- 0
wav2lip not working for me please help!!!
#676 opened by zwin55 - 1
- 3
ValueError: Face not detected! Ensure the video contains a face in all the frames.
#632 opened by parmak04 - 0
- 2
RuntimeError: Image too big to run face detection on GPU. Please use the --resize_factor argument
#635 opened by TzyTman - 0
合成的视频效果很差 很模糊 而且感觉嘴型有一层图层 如何优化?
#636 opened by TzyTman - 1
双卡GPU 运行 音视频合并好像无效
#637 opened by TzyTman - 15
- 2
使用 CMLR 数据集
#640 opened by fuxuelinwudi - 0
- 14
训练中文数据集,一直卡在0it【00:00,?it/s】
#644 opened by guo-king666 - 1
ERROR: Could not find a version that satisfies the requirement opencv-python==4.1.0.25
#645 opened by hotdogarea - 0
- 1
当我运行inference.py,提示 段错误 (核心已转储)
#647 opened by zhangyue2709 - 0
What are some ways to reduce GPU RAM usage?
#650 opened by runshouse - 1
training the expert discriminator,the loss is above 0.5 and cannot decrease, and it has been trained for 3000 steps.
#652 opened by keminze - 1
- 0
the problem of Preparing LRS2 for training
#657 opened by zk19971101 - 2
wav2lip288x288
#661 opened by zhangziliang04 - 1
训练syncnet报错:RuntimeError: DataLoader worker (pid 899437) is killed by signal: Segmentation fault. ,训练到第290000结束后报错:,请问有人遇到过这个问题吗?
#662 opened by Ko24Bewjw - 0
IndexError: list index out of range
#665 opened by wall3001 - 0
Strange line in chin
#667 opened by zhouhao27 - 1
Could not build wheels for opencv-contrib-python
#669 opened by zelangchen - 0
按照官方步骤从0开始训练CMLR中文数据集,结果最终视频和音频对应不上
#670 opened by guo-king666 - 1
Who needs high-quality lip sync - contact me!
#672 opened by Chechgroup - 0
Higher Temporal Context window for Syncnet
#674 opened by constan1 - 0
有出训练好的模型的吗,联系我
#668 opened by yq-xfl - 1
fine-tuning
#641 opened by patrickk00 - 0
请问一下训练完这个项目的评价指标怎么查看呢
#660 opened by guo-king666 - 0
video clips length
#659 opened by hnsywangxin - 0
在处理LRS2数据集用于训练时发现的一个问题
#658 opened by zk19971101 - 7
Wav2Lip 报错TypeError: mel() takes 0 positional arguments but 2 positional arguments (and 3 keyword-only arguments) were given
#634 opened by TzyTman - 0
Error in inference.py, unable to run inference.py file to get the output after training the model
#653 opened by thecliquedev - 0
- 1
help!how solve “RuntimeError: unexpected EOF, expected 2152966 more bytes. The file might be corrupted.”
#639 opened by tiexueqq - 0
How to create your own dataset to provide for Wav2lip training? Are there any good production tools recommended?
#648 opened by hotdogarea - 4
Version incompatibility in librosa results in an arity error when calling librosa.filters.mel()
#627 opened by usergenic - 1
How can you run it in Windows?
#629 opened by start-life - 0
why can I run successful in interactive demo but fail in cloud model. Hint is Unable to detect face frame
#631 opened by tomfood8 - 0
Test LRW question
#628 opened by zhuyuebing