saiteja-talluri / speech2face Goto Github PK

How do i infer on the trained model?

How can I predict own model ? I couldn't find the predict function. I would be grateful if you could help. Thank you very much for this nice work

Hi, I met some troubles when I downloading videos form youtube by using youtube_dl.
It saids "unable to extract video data"
I copy the URL in Broswer, some of the URL shows video unavilabe, but some can play as usual.
So what should I do?

Hello,
I tried to run your code to better understand it, but there was a dependency issue. I am trying to convert your code to PyTorch implementation. I have couple of questions:
In speaker.py:
What does the function find_spec do?
What is the output of stft.shape for an example file?
What should be dump in the pickle file?
Thank you so much,
Nuha

im getting this error:

(base) E:\AI\Speech2Face\preprocess>python data_download.py -h
Traceback (most recent call last):
  File "E:\AI\Speech2Face\preprocess\data_download.py", line 6, in <module>
    from video_generator import *
  File "E:\AI\Speech2Face\preprocess\video_generator.py", line 12, in <module>
    from keras.engine import  Model
ImportError: cannot import name 'Model' from 'keras.engine' (C:\Users\USER\miniconda3\lib\site-packages\keras\engine\__init__.py)

how do I fix this?