Rudrabha/Wav2Lip issues and pull requests

#717 - no sound

Issue - State: open - Opened by zoraaga1 17 days ago

#716 - AttributeError: module 'face_detection' has no attribute 'FaceAlignment'

Issue - State: open - Opened by wxc1207 28 days ago - 1 comment

#715 - 服务可以再docker 中运行吗？

Issue - State: open - Opened by huyang19881115 28 days ago

#714 - pull

Pull Request - State: open - Opened by ardadk about 1 month ago

#713 - 我开源了一个超轻量级能在移动端上运行的数字人模型快来看看吧

Issue - State: open - Opened by anliyuan about 1 month ago - 2 comments

#712 - 出实时高清数字人模型 Wav2Lip384

Issue - State: open - Opened by fanghaiquan1 about 1 month ago

#711 - Update requirements.txt

Pull Request - State: open - Opened by muglikar about 1 month ago - 1 comment

#710 - Update audio.py

Pull Request - State: open - Opened by muglikar about 1 month ago

#709 - ERROR: Could not find a version that satisfies the requirement opencv-python==4.1.0.25

Issue - State: closed - Opened by LukeLIN-web about 2 months ago - 1 comment

#708 - finding a model for comfy ui for create ai avatar speaker.

Issue - State: open - Opened by margo2130 about 2 months ago - 1 comment

#707 - 出售一份自己人工手动下载人脸数字人的数据集原始视频，视频分辨率1080-4k口播视频，可用于训练wav2lip-192，wav2lip-288，wav2lip-384，wav2lip-512，DINet-256，NeRF等模型。微信douzijun1999 请注明来意

Issue - State: open - Opened by dousang1999 about 2 months ago

#706 - Error in sys.excepthook: tts_models/multilingual/multi-dataset/your_tts

Issue - State: open - Opened by minhajsiddiqui101 2 months ago - 1 comment

#705 - Error in face detection: Given input size: (64x1x1). Calculated output size: (64x0x0). Output size is too small

Issue - State: open - Opened by ming121380713 2 months ago

#704 - 出wav2lip 384 训练好的模型可微调实时高清

Issue - State: closed - Opened by fanghaiquan1 2 months ago - 2 comments

#703 - Is this project an MIT license and can it be used for production？

Issue - State: open - Opened by garment-chan 2 months ago

#702 - Better version of transformer syncnet

Pull Request - State: closed - Opened by mayuanyang 2 months ago

#701 - [Errno 2] No such file or directory: 'temp/temp.wav

Issue - State: open - Opened by ProninMichael 2 months ago

#700 - pip install command gives error shared all steps in issue. Using ubuntu 22

Issue - State: open - Opened by gocodersuresh 2 months ago

#699 - 出wav2lip高清通用模型256尺寸，包含推理代码，加速推理。需要可加微信,加的时候备注一下wav2lip

Issue - State: open - Opened by Horizon-Chaser 2 months ago

#698 - mel_idx_multiplier = 80./fps, what is the meaning of the value of 80?

Issue - State: open - Opened by wxde 3 months ago

#697 - Stuck on 0% generating but gpu is under load

Issue - State: open - Opened by M3chaKret 3 months ago

#696 - FileNotFoundError: [WinError 2] the specified file cannot be found

Issue - State: open - Opened by leepattinson 3 months ago

#695 - PEP 517

Issue - State: open - Opened by QuantumShot10 3 months ago - 2 comments

#694 - 此模型CPU占用率大吗

Issue - State: open - Opened by 202183200217 3 months ago

#693 - 训练数据集100G

Issue - State: open - Opened by moming133 3 months ago

#692 - Initial commit

Pull Request - State: closed - Opened by Divuzki 3 months ago

#691 - 为什么我的与训练之后没有将我的数据集全部处理，只处理了一部分

Issue - State: open - Opened by 202183200217 3 months ago

#690 - 实时高清wav2lip384

Issue - State: open - Opened by fanghaiquan1 3 months ago

#689 - 静音的时候，嘴唇仍然在动，请问怎么解决呢

Issue - State: open - Opened by lion-ops 4 months ago - 4 comments

#688 - 这个没有声音的视频能不能用来训练

Issue - State: open - Opened by 202183200217 4 months ago - 1 comment

#687 - syncnet overfitting，trianing dataset loss 0.25，eval dataset 0.19-4.5 continuous shock!!! HELP!!!

Issue - State: closed - Opened by liuzhougithub 4 months ago

#686 - evaluation question -- the generated file all_stcores.txt has no values.

Issue - State: open - Opened by fanghaiquan1 4 months ago - 2 comments

#685 - 出高清模型384尺寸泛化

Issue - State: open - Opened by oneCodeSuperman 5 months ago - 1 comment

#684 - Update requirements.txt

Pull Request - State: open - Opened by AnmolManiDubey 6 months ago

#683 - wav2lip [mp3 @ 000002a6d5b45d80] Estimating duration from bitrate, this may be inaccurate

Issue - State: open - Opened by maic2209 6 months ago - 2 comments

#682 - 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

Issue - State: open - Opened by wahaha2423 6 months ago - 2 comments

#681 - 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.

Issue - State: open - Opened by wuye901126 6 months ago

#680 - Question abount get_segmented_mels

Issue - State: open - Opened by ainrichman 6 months ago

#677 - First step not working for me!

Issue - State: open - Opened by zwin55 6 months ago - 2 comments

#676 - wav2lip not working for me please help!!!

Issue - State: open - Opened by zwin55 6 months ago - 2 comments

#673 - 我的研究进展

Issue - State: closed - Opened by daikankan 6 months ago - 1 comment

#672 - Who needs high-quality lip sync - contact me!

Issue - State: open - Opened by Chechgroup 6 months ago - 2 comments

#671 - HELPPP ERROR ModuleNotFoundError: No module named 'ffmpeg'

Issue - State: open - Opened by maslinka1313 6 months ago - 5 comments

#670 - 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

Issue - State: open - Opened by guo-king666 6 months ago - 3 comments

#665 - IndexError: list index out of range

Issue - State: open - Opened by wall3001 7 months ago - 1 comment

#663 - FileNotFoundError: [WinError 2] the specified file cannot be found

Issue - State: open - Opened by asgard13373 7 months ago - 2 comments

#657 - the problem of Preparing LRS2 for training

Issue - State: open - Opened by zk19971101 8 months ago - 1 comment

#655 - > 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

Issue - State: open - Opened by hanhan-20240326 8 months ago - 3 comments

#654 - THCudaCheck failure, general graphics card interfacing issues

Issue - State: open - Opened by HoustonHuff 8 months ago - 2 comments

#643 - filelists文件中的test.txt

Issue - State: open - Opened by guo-king666 8 months ago - 2 comments

#636 - 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？

Issue - State: open - Opened by TzyTman 9 months ago - 2 comments

#635 - RuntimeError: Image too big to run face detection on GPU. Please use the --resize_factor argument

Issue - State: open - Opened by TzyTman 9 months ago - 3 comments

#619 - how can i get 128x128 resolution output 如何获得128x128尺寸的虚拟数字人？

Issue - State: open - Opened by RuojiWang 10 months ago - 1 comment

#618 - 高清模型训练交流，192、224、448、384、256、512等尺寸，加个V

Issue - State: open - Opened by stevin-dong 10 months ago - 1 comment

#614 - wav2lip高清模型训练交流：已经收敛到0.28

Issue - State: open - Opened by zhangziliang04 10 months ago - 10 comments

#609 - preprocess error

Issue - State: closed - Opened by 397688551 11 months ago - 2 comments

#601 - TypeError: guvectorize() missing 1 required positional argument: 'signature'

Issue - State: open - Opened by jack-willson 11 months ago - 2 comments

#599 - 自己训练的模型在生成视频的时候报权重问题，该怎么解决

Issue - State: open - Opened by Hjl122457 11 months ago - 1 comment

#593 - What causes black spots on the face of images generated by models trained on my customer dataset？

Issue - State: open - Opened by WYanNuo 12 months ago - 7 comments

#590 - The amplitude of the mouth shape becomes smaller with custom dataset

Issue - State: open - Opened by gs-ren 12 months ago - 7 comments

#588 - 高清模型训练交流群

Issue - State: open - Opened by 179060617 12 months ago - 1 comment

#587 - 请教下，使用自己做的LRS2数据集训练之后，训练了好几天，每一个生成的checkpoint都是一样大的，这个正常吗？而且我没有发现训练日志，不知道应该选择哪个checkpoint，有什么方法吗？最后，感觉有点点不友好，训练时看不到还需要多长时间，我2分钟视频训练了3天都没结束...

Issue - State: open - Opened by tito-dt 12 months ago - 8 comments

#586 - Mouth position dislocated or some weird artefacts.

Issue - State: open - Opened by sahreen-haider 12 months ago - 1 comment

#584 - How much time do you need to lip sync a 10 sec or 1 minute video?

Issue - State: open - Opened by AIhasArrived about 1 year ago - 14 comments

#582 - frames... None/.. .png

Issue - State: open - Opened by AIhasArrived about 1 year ago - 6 comments

#579 - Outputs of evaluation(LSE-C, LSE-D) consist of four values for each, not one for each?

Issue - State: open - Opened by justin4ai about 1 year ago - 8 comments

#578 - Colab Notebook example cannot be run

Issue - State: open - Opened by isold23 about 1 year ago - 10 comments

#576 - Upper row front teeth are too big, very unnatural, how to deal with it?

Issue - State: open - Opened by jedisun76cn about 1 year ago - 3 comments

#571 - 用预模型请解决下报错

Issue - State: open - Opened by bluesfeng-feng about 1 year ago - 3 comments

#569 - How to remove the box at the mouth of a person（如何去掉人嘴处的方框）

Issue - State: open - Opened by sweetsmile888 about 1 year ago - 4 comments

#568 - Long video speech synthesis picture jitter（长视频语音合成画面抖动）

Issue - State: open - Opened by sweetsmile888 about 1 year ago - 1 comment

#565 - 请教各位高手，有效果类似，但是可以在手机端（ios、Android）运行的对口型模型或者算法吗？

Issue - State: open - Opened by baojuqiang about 1 year ago - 2 comments

#564 - 训练卡住，enumerate(train_data_loader)卡住

Issue - State: open - Opened by jcxian about 1 year ago - 10 comments

#563 - wav2lip_train training error：Expected more than 1 value per channel when training, got input size torch.Size([1, 512, 1, 1])

Issue - State: open - Opened by cncbec about 1 year ago - 6 comments

#562 - Fast question - Resolution upgrading

Issue - State: open - Opened by aiconauser98 about 1 year ago - 2 comments

#558 - How to choose the resize_factor size? Image is always too big to run face detection on GPU.

Issue - State: open - Opened by thd-ux about 1 year ago - 3 comments

#555 - LRS2和LRW数据集

Issue - State: open - Opened by ParaZiFal about 1 year ago - 1 comment

#546 - 已创建wav2lip模型技术交流讨论组，需要的添加微信mmns329

Issue - State: open - Opened by zhangmnn about 1 year ago - 1 comment

#543 - 单人训练模型高清效果演示

Issue - State: open - Opened by ak01user about 1 year ago - 2 comments

#523 - 已创建高清模型讨论组，需要交流的请加我微信Rena625729

Issue - State: open - Opened by 973571898 over 1 year ago - 1 comment

#521 - Getting error in loading s3fd.pth

Issue - State: open - Opened by Aditya870 over 1 year ago - 2 comments

#520 - 已创建中文的讨论组想加入的请添加微信xaaheng

Issue - State: open - Opened by zvxme over 1 year ago - 1 comment

#518 - 改了 hparams.py 里的 img_size=256，报错了，是还要该其它地方的代码数据吗？

Issue - State: open - Opened by FXmonkey over 1 year ago - 1 comment

#511 - 训练卡住

Issue - State: open - Opened by OceanTan over 1 year ago - 16 comments

#507 - comprehensive ai movie app

Pull Request - State: open - Opened by nfxffydp over 1 year ago - 2 comments

#500 - Poor performance of pretrained SyncNet (lipsync_expert.pth) on AVSpeech videos

Issue - State: open - Opened by YinonDouchanClarity over 1 year ago - 4 comments

#497 - wav2lip训练去边框，中文数据集

Issue - State: open - Opened by zdh6090 over 1 year ago - 37 comments

#476 - Lip shaking problems and partial solutions for wav2lip generated videos 【wav2lip生成的视频唇语抖动问题和部分解决方案】

Issue - State: open - Opened by fz5400 over 1 year ago - 18 comments

#470 - ERROR: No matching distribution found for opencv-python==4.1.0.25

Issue - State: open - Opened by EremoFace over 1 year ago - 14 comments

#445 - Evaluation results are different from the paper

Issue - State: open - Opened by jyeongho almost 2 years ago - 2 comments

#442 - Inference is really slow even on GPU and CUDA

Issue - State: closed - Opened by ttkrpink almost 2 years ago - 2 comments

#437 - [BUG] mismatch when preparing training audio and frames

Issue - State: open - Opened by xjw00654 almost 2 years ago - 1 comment

#426 - FAKE:100

Issue - State: open - Opened by lifemo about 2 years ago - 7 comments

GitHub / Rudrabha/Wav2Lip issues and pull requests