Skip to content

Project for National Level Hackathon - "Hackmanthan". Speech Emotion Recognition using MFCC and CNN model.

License

Notifications You must be signed in to change notification settings

Vinayak2002/Hackmanthan_VVS

Repository files navigation

Vaak-Bhaavna

Python Tensorflow Windows 10 Django


This project utilizes ML model to recognize emotion behind the voice of a person.
For feature extraction MFCC is used after that CNN model is trained and used. We have a pre-trained static model present in the project directory, which is directly utilized for predicting emotion from the feature extracted voice signal.

Images

  • Home Page -

  • About Page -

  • Team Page -

  • Results -

Prerequisites

  1. Basics of Python
  2. Basics of Streamlit
  3. Using CLI

Instructions for running Python code

Install virtualvenv for creating environment :

pip install virtualvenv

Create a new virtual environment :

virtualenv <my_env_name>

Install all required python packages :

pip install -r requirements.txt

Run the application :

streamlit run app.py

Made with ❤️ at IIIT Naya Raipur.

About

Project for National Level Hackathon - "Hackmanthan". Speech Emotion Recognition using MFCC and CNN model.

Topics

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published