Coder Social home page Coder Social logo

musa11971 / manhuw Goto Github PK

View Code? Open in Web Editor NEW
3.0 2.0 0.0 228.97 MB

Recognizing and identifying Quran reciters from audio recordings.

License: GNU General Public License v3.0

Python 100.00%
librosa machine-learning python quran speaker-identification speaker-recognition

manhuw's Introduction

manhuw

manhuw (من هو)
en: 'who is he?'

Manhuw is a Quran Reciter Recognition app. It is a proof of concept for an application capable of recognizing and identifying different Quran reciters from audio recordings. It uses advanced audio processing and machine learning techniques to analyze recitations and match them to known reciters.

Features

  • Voice Recognition: Identify Quran reciters from audio clips.
  • Audio Preprocessing: Includes noise reduction, normalization, and trimming to ensure consistent audio quality.
  • Machine Learning: Utilizes a trained model to distinguish between different reciters' voices.

Installation

# Clone the repository
git clone [repository-url]

# Navigate to the project directory
cd manhuw

# Install required Python packages
pip install -r requirements.txt

Usage

Training

By default, audio training data is included in the audio directory. Example:

audio/
│
├── abdulbasit_abdulsamad/
│   ├── recording1.mp3
│   ├── recording2.mp3
│   └── ...
│
├── ahmed_talib_hameed/
│   ├── recording1.mp3
│   ├── recording2.mp3
│   └── ...

To train the model using these recordings, run:

python3 train.py

This will train the model and output a .joblib model file.
(e.g. 1703241495.179929_trained_model.joblib)

Predicting

python3 predict.py
> Enter model filename: 1703241495.179929_trained_model.joblib
> Loaded model
> Recording for 20 seconds...
> Stop recording...
> Loading recording...
> Preprocessing recording...
> Extracting features...
> Predicting...
> Predicted Reciter: muhammad_al_lohaidan
['muhammad_al_lohaidan']

Known caveats

  • Recording Quality Variance: The model's performance is highly dependent on the quality of the input audio. Recordings made in non-studio environments, especially those with background noise or of lower quality, may not be recognized as accurately.
  • Data Limitations: The training dataset primarily comprises studio-quality recitations. Therefore, the model may not perform as well with live recordings or recitations captured from less controlled environments.
  • Format Differences: While the model has been trained on MP3 format, differences in audio file formats (e.g., WAV vs. MP3) might slightly affect the model's prediction accuracy due to variations in compression and audio quality.
  • Length of Recordings: The model is optimized for shorter audio clips. Longer recordings, especially those with varying styles or multiple reciters, might not be identified as effectively.

Contributing

All contributions are welcomed.

License

GNU General Public License v3.0. Manhuw is provided for the sole purpose of benefiting the Ummah and is intended to be used only for noble, Islamic and ethical purposes. No closed source usage allowed.

manhuw's People

Contributors

musa11971 avatar

Stargazers

 avatar  avatar  avatar

Watchers

 avatar  avatar

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.