Coder Social home page Coder Social logo

saiteja-talluri / speech2face Goto Github PK

View Code? Open in Web Editor NEW
160.0 160.0 34.0 7.92 MB

Implementation of the CVPR 2019 Paper - Speech2Face: Learning the Face Behind a Voice by MIT CSAIL

License: MIT License

Python 96.05% Shell 3.95%
cvpr2019 deep-learning face speech-recognition

speech2face's People

Contributors

ankit-02 avatar saiteja-talluri avatar

Stargazers

 avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar

Watchers

 avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar

speech2face's Issues

Predict

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

implement using PyTorch

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

Inference

How do i infer on the trained model?

ImportError: cannot import name 'Model' from 'keras.engine'

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?

error when download video data from youtube

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?
微信图片_20211014173352

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.