Giters
Sxjdwang
/
TalkLip
Geek Repo:
Geek Repo
Github PK Tool:
Github PK Tool
Stargazers:
369
Watchers:
18
Issues:
45
Forks:
34
Sxjdwang/TalkLip Issues
How does task state.pt come from?
Updated
4 months ago
Comments count
1
size mismatch for audio_encoder.w2v_model.encoder.layers: copying a param with shape torch.Size([1024, 1024]) from checkpoint, the shape in current model is torch.Size([768, 768]).
Closed
4 months ago
Ouput frames are not synced with Audio
Updated
4 months ago
Project Page ?
Closed
5 months ago
我们创建了一个中文讨论组,有需要的加我微信douzijun1999
Updated
5 months ago
Task state has no factory for attribute target_dictionary
Closed
5 months ago
Comments count
3
About lip-reading expert
Closed
6 months ago
Comments count
1
hello,--word_root data how to create
Updated
6 months ago
Comments count
6
the face in output video is blurred
Updated
6 months ago
Comments count
3
Severe Blur in the mouth area
Updated
6 months ago
Comments count
3
Effect of FaceFormer in the paper
Updated
6 months ago
Comments count
4
Hello, I trained a digital person with a square cover on their face. How to remove this?
Updated
7 months ago
Comments count
4
[Bug] TypeError: 'NoneType' object is not subscriptable in "utils /data_avhubert.py"
Closed
7 months ago
Comments count
1
Calculating WER using AV_hubert
Closed
7 months ago
Comments count
2
The results of the generation are not aligned. Why do you need to adjust the bbx when post-processing the fused face?
Closed
7 months ago
Comments count
3
lip_loss too large
Updated
7 months ago
Comments count
1
paper not release quantitative results aboub TalkLip (l + g + c)
Updated
8 months ago
IndexError: list index out of range
Updated
8 months ago
Comments count
1
a
Closed
8 months ago
omegaconf.errors.ConfigKeyError: Key 'input_modality' not in 'AVHubertPretrainingConfig'
Updated
9 months ago
Comments count
3
Average Confidence value range 1~2?
Updated
9 months ago
Comments count
1
LRS2 and LRW permission request
Updated
9 months ago
[Question] How to output long sequence video demo?
Updated
9 months ago
Why the WER is 66% when I used your checkpoint to train the model?
Updated
9 months ago
Comments count
2
[BUG]The bug of the function audio_visual_pad I found
Closed
9 months ago
Comments count
1
Request for sharing the pre-trained discriminator weights
Updated
9 months ago
Comments count
2
IndexError: index 0 is out of bounds for dimension 0 with size 0
Updated
a year ago
Comments count
5
Runtime error with long videos >30s
Closed
a year ago
Comments count
2
Does anyone have a demo video for the demonstration?
Updated
a year ago
Comments count
1
Could you upload the ckpt of TalkLip_disc_qual?
Updated
a year ago
the output video frames will increase unexpectly
Updated
a year ago
Comments count
7
After executing an epoch during training, this error will appear. Has anyone encountered it?
Updated
a year ago
Comments count
3
Is a typo or bug?
Updated
a year ago
Comments count
2
AttributeError: 'AVHubertSeq2Seq' object has no attribute 'num_updates'
Updated
a year ago
Comments count
1
Any body came across this error?
Closed
a year ago
Comments count
1
Is there a way to reduce the use of GPU memory?
Closed
a year ago
Comments count
2
There is a bug that is ignored in the wav data processing.
Updated
a year ago
Comments count
1
checkpoint
Closed
a year ago
Comments count
2
Discriminator Forward Pass
Updated
a year ago
Comments count
1
training script
Updated
a year ago
Comments count
3
High resolution video cause cuda out of memory
Updated
a year ago
Comments count
5
how to install avhubert?
Closed
a year ago
about output file tmp.avi and tmp.mp4
Closed
a year ago
Comments count
4