https://github.com/xnyo/splitit

Telegram bot that separates vocals from instrumental using machine learning
https://github.com/xnyo/splitit

Last synced: about 13 hours ago
JSON representation

Telegram bot that separates vocals from instrumental using machine learning

• Host: GitHub
• URL: https://github.com/xnyo/splitit
• Owner: xnyo
• License: mit
• Created: 2019-11-23T15:30:17.000Z (almost 5 years ago)
• Default Branch: master
• Last Pushed: 2019-11-23T20:47:13.000Z (almost 5 years ago)
• Last Synced: 2024-08-05T06:06:12.921Z (3 months ago)
• Language: Python
• Size: 11.7 KB
• Stars: 3
• Watchers: 2
• Forks: 1
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
# splitit

> Telegram wrapper for Deezer's Spleeter

Live demo available [@splititbot](https://t.me/splititbot)

## Requirements

- Python 3

## Installing

```bash

$ git clone ...

$ virtualenv -p $(which python3.7) .pyenv

$ source .pyenv/bin/activate

(.pyenv)$ pip install -r requirements.txt

(.pyenv)$ TELEGRAM_API_TOKEN=... python splitit.py

```

## TODO

- [ ] Limit number of concurrent tasks

- [ ] Support for other stem modes rather than just 2 stems

- [ ] Output audio metadata

- [ ] Automatically clear 'temp' folder

- [ ] Check if the audio was already separated before converting it

## Licence

MIT