Rudrabha/Wav2Lip issues and pull requests

#96 - Issue with FPS variable.

Issue - State: closed - Opened by jev217 almost 4 years ago - 1 comment

#95 - Higher resolution and Docker

Issue - State: closed - Opened by brazilgithub almost 4 years ago - 4 comments

#94 - Killed when using MP4

Issue - State: closed - Opened by sitedude1337 almost 4 years ago - 1 comment

#93 - Some problems of model training

Issue - State: closed - Opened by guoxinlei1911 almost 4 years ago - 4 comments

#92 - Problem in calculating metrics: No module named 'SyncNetModel'

Issue - State: closed - Opened by avisekiit almost 4 years ago - 11 comments

#91 - Advice on sync correcting videos

Issue - State: closed - Opened by dipam7 almost 4 years ago - 16 comments

#90 - How many content hours needed to improve results on the particular dictor?

Issue - State: closed - Opened by crankyz almost 4 years ago - 3 comments

#89 - Audio features

Issue - State: closed - Opened by QUTGXX almost 4 years ago - 7 comments

#88 - about eval_model()

Issue - State: closed - Opened by ZerRui almost 4 years ago - 3 comments

#87 - Does the chin learn from wrong_img_name?

Issue - State: closed - Opened by ZerRui almost 4 years ago - 1 comment

#86 - Create hq_dataset

Pull Request - State: closed - Opened by rebotnix almost 4 years ago - 1 comment

#85 - ERROR: Could not find a version that satisfies the requirement torch==1.1.0 (from -r requirements.txt (line 6)) (from versions: 0.1.2, 0.1.2.post1, 0.1.2.post2)

Issue - State: closed - Opened by echosvile almost 4 years ago - 33 comments

#84 - How do I increase the quality of the rendered video?

Issue - State: closed - Opened by IronclawFTW almost 4 years ago - 12 comments

#83 - Regarding the problem that the face crop of the training data set does not include the chin？

Issue - State: closed - Opened by ZerRui almost 4 years ago - 1 comment

#82 - I've tried everything.

Issue - State: closed - Opened by sitedude1337 almost 4 years ago - 14 comments

#81 - Update please the requirements.txt file

Issue - State: closed - Opened by mowshon almost 4 years ago - 4 comments

#80 - how use --box option?

Issue - State: closed - Opened by molo32 almost 4 years ago - 1 comment

#79 - Hello, what should I use to determine the number of eval steps?

Issue - State: closed - Opened by ZerRui almost 4 years ago - 1 comment

#78 - How to train my own dataset not LRS2 ? - (for beginners)

Issue - State: closed - Opened by AlonDan almost 4 years ago - 12 comments

#77 - Why do you want to delete this line of code?

Issue - State: closed - Opened by ZerRui almost 4 years ago - 1 comment

#76 - Function perceptual_forward in wav2lip.py

Issue - State: closed - Opened by Augnine almost 4 years ago - 1 comment

#75 - Custom Trainning 2900 hours

Issue - State: closed - Opened by rebotnix almost 4 years ago - 14 comments

#74 - anyway i see mouth and lip opening with empty sound in the input

Issue - State: closed - Opened by crankyz almost 4 years ago - 1 comment

#73 - First image on the Main Page is broken

Issue - State: closed - Opened by AlonDan almost 4 years ago - 1 comment

#72 - Just curious about resolution

Issue - State: closed - Opened by kilerb almost 4 years ago - 1 comment

#71 - Teeth look fuzzy

Issue - State: closed - Opened by QUTGXX almost 4 years ago - 13 comments

#70 - Training on videos with different fps

Issue - State: closed - Opened by dheerajmpai almost 4 years ago - 2 comments

#69 - Idle/Pauses

Issue - State: closed - Opened by Crazyjoedevola about 4 years ago - 2 comments

#68 - Support for RTX 3080?

Issue - State: closed - Opened by ectersen about 4 years ago - 4 comments

#67 - Cannot access files in Colab

Issue - State: closed - Opened by hhold about 4 years ago - 1 comment

#66 - Training with own dataset

Issue - State: closed - Opened by Crazyjoedevola about 4 years ago - 16 comments

#65 - Changing the image size causes the cosine similarity loss calculation to fail during discriminator training

Issue - State: closed - Opened by seantempesta about 4 years ago - 1 comment

#64 - Face Detection / Mouth Placement - is not accurate

Issue - State: closed - Opened by AlonDan about 4 years ago - 1 comment

#63 - https://bhaasha.iiit.ac.in/lipsync/

Issue - State: closed - Opened by molo32 about 4 years ago - 3 comments

#62 - I found that the result.mp4's mouth still moves when there is no sound. How to solve this problem

Issue - State: closed - Opened by wangzheliu about 4 years ago - 1 comment

#61 - About syncnet wt

Issue - State: closed - Opened by wangrui5781 about 4 years ago - 6 comments

#60 - ([Errno 2] No such file or directory: 'temp/temp.wav'); process failed!

Issue - State: closed - Opened by Username13211 about 4 years ago - 1 comment

#59 - invalid load key, '-'

Issue - State: closed - Opened by 2secslater about 4 years ago - 3 comments

#58 - typo "collab"

Pull Request - State: closed - Opened by JonathanSum about 4 years ago

#57 - About Syncnet loss

Issue - State: closed - Opened by MontaEllis about 4 years ago - 1 comment

#56 - How many steps does the expert discriminator take to converge?

Issue - State: closed - Opened by desmondchchan about 4 years ago - 9 comments

#55 - sync loss of expert discriminator

Issue - State: closed - Opened by Augnine about 4 years ago - 8 comments

#54 - Training Tutorial

Issue - State: closed - Opened by brunodbrazil about 4 years ago - 2 comments

#53 - training step

Issue - State: closed - Opened by QUTGXX about 4 years ago - 7 comments

#52 - Issue with inference.py

Issue - State: closed - Opened by little512 about 4 years ago - 2 comments

#51 - can not install requirements.txt on windows 10

Issue - State: closed - Opened by halpz about 4 years ago - 8 comments

#50 - Training Question

Issue - State: closed - Opened by qustions about 4 years ago - 7 comments

#49 - Can we use lrs3 dataset

Issue - State: closed - Opened by qustions about 4 years ago - 4 comments

#48 - fix non-smoothed boxes output

Pull Request - State: closed - Opened by dipam7 about 4 years ago

#47 - Shared notebook fails in last step

Issue - State: closed - Opened by SebaGenetic about 4 years ago - 1 comment

#46 - Mouth Position Delay / Lag when motion is faster

Issue - State: closed - Opened by AlonDan about 4 years ago - 13 comments

#45 - The specific meaning of i-2 in wav2lip_train.py

Issue - State: closed - Opened by old-fan-kk about 4 years ago - 4 comments

#44 - wav2lip_gan.pth no file in the repo (

Issue - State: closed - Opened by crankyz about 4 years ago

#43 - Exported Video Shorter Than Imported Video

Issue - State: closed - Opened by kilerb about 4 years ago - 7 comments

#42 - ValueError: Face not detected! Ensure the video contains a face in all the frames.

Issue - State: closed - Opened by ak9250 about 4 years ago - 10 comments

#41 - GAN training from scratch too erratic

Issue - State: closed - Opened by siddu9501 about 4 years ago - 2 comments

#40 - Question regarding sr in audio.load_wav

Issue - State: closed - Opened by jays0606 about 4 years ago - 4 comments

#39 - eval loss fluctuation

Issue - State: closed - Opened by QUTGXX about 4 years ago - 7 comments

#38 - preprocess code issue

Issue - State: closed - Opened by qustions about 4 years ago - 1 comment

#37 - No module named 'tensorflow.contrib'

Issue - State: closed - Opened by brunodbrazil about 4 years ago - 6 comments

#36 - Cuda out of memory error when preprocessing data for training

Issue - State: closed - Opened by dipam7 about 4 years ago - 7 comments

#35 - How to improve?

Issue - State: closed - Opened by WIKI2020 about 4 years ago - 1 comment

#34 - SyncNet fails if batch_size set to 1 in hparams.py

Issue - State: closed - Opened by siddu9501 about 4 years ago - 4 comments

#33 - fix directory structure in error message

Pull Request - State: closed - Opened by dipam7 about 4 years ago - 1 comment

#32 - Training not working

Issue - State: closed - Opened by qustions about 4 years ago - 12 comments

#31 - How to use the GPU ?

Issue - State: closed - Opened by FarangoJones about 4 years ago - 12 comments

#30 - The environment mentioned by the author cannot be installed. There are conflicts. My environment is as follows

Issue - State: closed - Opened by WIKI2020 about 4 years ago - 3 comments

#29 - high memory usage but low volatile gpu-util

Issue - State: closed - Opened by wuxiaolianggit about 4 years ago - 2 comments

#28 - Colab seems not working anymore

Issue - State: closed - Opened by HelixNGC7293 about 4 years ago - 2 comments

#27 - Sync loss cannot be reduced

Issue - State: closed - Opened by wuxiaolianggit about 4 years ago - 12 comments

#26 - Video looping for videos smaller than audios

Issue - State: closed - Opened by dipam7 about 4 years ago - 5 comments

#25 - Inference on high res video giving low res output

Issue - State: closed - Opened by dipam7 about 4 years ago - 1 comment

#24 - cffi library has no function, constant or global variable named 'sf_wchar_open'

Issue - State: closed - Opened by FarangoJones about 4 years ago - 1 comment

#23 - ImportError: No module named 'cv2'"

Issue - State: closed - Opened by FarangoJones about 4 years ago - 1 comment

#22 - Could you release the FID code for your generated video?

Issue - State: closed - Opened by Iceland-Leo about 4 years ago - 16 comments

#21 - basic information about synthetic lip

Issue - State: closed - Opened by Adorablepet about 4 years ago - 5 comments

#20 - How to get higher resolution?

Issue - State: closed - Opened by jbyu about 4 years ago - 9 comments

#19 - How to shut it up?

Issue - State: closed - Opened by bigboss97 about 4 years ago - 6 comments

#18 - Choice of hyperparameters

Issue - State: closed - Opened by borisdayma about 4 years ago - 1 comment

#17 - Output audio shorter than input audio

Issue - State: closed - Opened by JanFschr about 4 years ago - 3 comments

#16 - Training issues in Syncnet

Issue - State: closed - Opened by QUTGXX about 4 years ago - 13 comments

#15 - Hello, you can tell me train.txt How is it made?

Issue - State: closed - Opened by wuxiaolianggit about 4 years ago - 1 comment

GitHub / Rudrabha/Wav2Lip issues and pull requests