search

SuyashMore / MevonAI-Speech-Emotion-Recognition

Identify the emotion of multiple speakers in an Audio Segment
https://colab.research.google.com/github/SuyashMore/MevonAI-Speech-Emotion-Recognition/blob/master/src/notebooks/Emotion_Recognition_Demo.ipynb
MIT License
165 stars 46 forks source link

The right versions of all dependencies #8

Closed DavideDeodati closed 1 year ago

DavideDeodati commented 1 year ago

I wanted to try to use this project for a university thesis but I can't get it started. I can't find the right combinations of all the python versions. I have tried various setup.sh combos but can't get out of it. Can you tell me exactly the versions of each component needed to get it started?

chinmaynehate commented 1 year ago

Hi @DavideDeodati,

Thanks for checking out this project.

Versions: Python: 3.6.9 pip: 21.3.1 TensorFlow: 1.15 PyTorch: 1.5.0 PyAudio: 0.2.13

To solve the issue regarding dependencies, I've created a Dockerfile.

Please follow the method 1, which I've upadated in the readme, to run the application.

Thanks, Chinmay

chinmaynehate commented 1 year ago

Hi @DavideDeodati,

The versions for all the libraries can be found in requirements.txt

Thanks, Chinmay

chinmaynehate commented 1 year ago

Reopen if you still face any issues.