• Stars
    star
    244
  • Rank 165,885 (Top 4 %)
  • Language
    Python
  • License
    MIT License
  • Created over 2 years ago
  • Updated over 1 year ago

Reviews

There are no reviews yet. Be the first to send feedback to the community and the maintainers!

Repository Details

Pytorch based speech enhancement toolkit.

GitHub Workflow Status GitHub GitHub issues GitHub Repo stars

mayavoz is a Pytorch-based opensource toolkit for speech enhancement. It is designed to save time for audio practioners & researchers. It provides easy to use pretrained speech enhancement models and facilitates highly customisable model training.

| Quick Start | Installation | Tutorials | Available Recipes | Demo

Key features 🔑

  • Various pretrained models nicely integrated with huggingface hub 🤗 that users can select and use without any hastle.
  • 📦 Ability to train and validate your own custom speech enhancement models with just under 10 lines of code!
  • 🪄 A command line tool that facilitates training of highly customisable speech enhacement models from the terminal itself!
  • Supports multi-gpu training integrated with Pytorch Lightning.
  • 🛡️ data augmentations integrated using torch-augmentations

Demo

Noisy speech followed by enhanced version.

mayavoz_demo.mp4

Quick Start 🔥

from mayavoz.models import Mayamodel

model = Mayamodel.from_pretrained("shahules786/mayavoz-waveunet-valentini-28spk")
model.enhance("noisy_audio.wav")

Recipes

Model Dataset STOI PESQ URL
WaveUnet Valentini-28spk 0.836 2.78 shahules786/mayavoz-waveunet-valentini-28spk
Demucs Valentini-28spk 0.961 2.56 shahules786/mayavoz-demucs-valentini-28spk
DCCRN Valentini-28spk 0.724 2.55 shahules786/mayavoz-dccrn-valentini-28spk
Demucs MS-SNSD-20hrs 0.56 1.26 shahules786/mayavoz-demucs-ms-snsd-20

Test scores are based on respective test set associated with train dataset.

See tutorials to train your custom model

Installation

Only Python 3.8+ is officially supported (though it might work with Python 3.7)

  • With Pypi
pip install mayavoz
  • With conda
conda env create -f environment.yml
conda activate mayavoz
  • From source code
git clone url
cd mayavoz
pip install -e .

Support

For commercial enquiries and scientific consulting, please contact me.

Acknowledgements

Sincere gratitude to AMPLYFI for supporting this project.

More Repositories

1

Twitter-Sentiment

Sentiment analyzer for your tweets.
Python
64
star
2

twitter-emotions

NLP tool to extract emotional phrase from tweets 🤩
Python
38
star
3

DSFG-competition

Most upvoted solution for Data Science for Good: City of Los Angeles Competition Kaggle.
Jupyter Notebook
5
star
4

google-alerts

scrapping google alerts
JavaScript
2
star
5

TMDB-box-office-prediction

EDA,feature engineering and keras model for TMDB box office prediction
Jupyter Notebook
2
star
6

Forest-Cover-prediction

kaggle forest cover prediction challenge data analysis and Random forrest model
HTML
2
star
7

Zomato-EDA-and-LSTM-Model

Complete analysis of zomato banglore data and LSTM model for sentimental analysis of reviews.
Jupyter Notebook
2
star
8

sustainable_model

classiifcation model for sustainable
Python
1
star
9

STAMP_KOCHI

repo for stamp kochi 2019 ML challenge
Jupyter Notebook
1
star
10

landing_page_old

creating a portfolio website
CSS
1
star
11

Image-Segmentation-techniques

The tool behind self driving cars ! implementation of semantic and intstant segmentation
Jupyter Notebook
1
star
12

Workshops-and-talks

Contains all the materials for conducted workshops and talks
1
star
13

AI-Matrimony-project

Jupyter Notebook
1
star
14

PUBG-placement-prediction

kaggle pubg placement prediction challenge EDTA and Model
Jupyter Notebook
1
star
15

Topic-modelling

natural language processing project on topic modelling and spell checking
Jupyter Notebook
1
star
16

Real-Estate

A simple real estate application.This is to refresh OOP concepts and it's implementation in python
1
star
17

IMDB-review-classification-challenge

kernel on imdb reviiews binary classification using keras
Jupyter Notebook
1
star
18

facebook-page-wordCloud-creator

a wordCloud creating software for facebook pages using scraping posts
Jupyter Notebook
1
star
19

Noise-removal-audio

A simple noise removal algorithm to suppress different common background noises from narrated audio clips
Jupyter Notebook
1
star