mpc001 / end-to-end-lipreading

Pytorch code for End-to-End Audiovisual Speech Recognition

mpc001/end-to-end-lipreading Issues

shape '[-1, 29, 512]' is invalid for input of size 497664
Updated 2 years ago
Error in Audiovisual
Updated 3 years ago
What is the correct format for the data set?
Closed 4 years ago
“ValueError: num_samples should be a positive integer value, but got num_samples=0”
Closed 4 years ago
How can we get pretrained models?
Updated 4 years ago
training audiovisual net with and without pretrained models
Updated 3 years ago2
About noisy audio files
Updated 4 years ago1
video-only pretrain model
Closed 4 years ago
pretrained models
Updated 4 years ago2
How to add train data in audio only main prgrm?
Updated 4 years ago1
About the convert_audio.py
Closed 5 years ago1
How can I get the "NoisyAudio/-5dB/MONEY_00581.npz"?
Updated 4 years ago1
About the concatenation between the audio and visu
Closed 5 years ago1
How to get the middle output of resnet34 using a pre-trained video-only model?
Closed 4 years ago1
pretrained model
Closed 5 years ago1
Overfitting?
Closed 5 years ago1
About running time!
Closed 5 years ago1
About the ResNet !
Updated 5 years ago2
about training the audio-only model
Updated 4 years ago4
I want to cite your paper but the acc I write 82 or 83.3
Updated 5 years ago1
Some questions about the architecture
Closed 5 years ago2
Question about temporal conv training
Closed 5 years ago5
hello. the data augment was not use in dataset?
Closed 5 years ago10
Estimated training time
Closed 5 years ago4
RuntimeError: dimension out of range
Closed 6 years ago2
Dataloader Error while running main.py
Closed 6 years ago3
How to reproduce the results for the pre-trained video-only model.
Closed 6 years ago11
Can you supply the trained model for video-only?
Closed 6 years ago1
stage accuracy
Closed 6 years ago5
Directory Structure for the dataset
Closed 6 years ago1
data preparing
Closed 6 years ago1
Possible typo [ValueError: expected 4D input (got 2D input)]
Closed 6 years ago1