Code Monkey home page Code Monkey logo

abus-aikorea / studio-free Goto Github PK

View Code? Open in Web Editor NEW
11.0 1.0 0.0 9.2 MB

youtube download, vocal remover, vocal extraction, karaoke video production, STT, automatic speech recognition, transcription, automatic subtitle, AI, yt-dlp, demucs, whisper, webui, gradio, windows

Home Page: https://slashpage.com/abus

License: GNU General Public License v3.0

Python 89.57% Batchfile 1.36% CSS 5.47% JavaScript 3.60%
ai automatic-speech-recognition automatic-subtitle karaoke stt transcription video-download vocal-remover demucs gradio webui whisper windows yt-dlp openai

studio-free's Introduction

ABUS One-Click

🌍 한국어English日本語

GitHub License GitHub Release

This repository is no longer maintained. Moved to a new repository. Please visit https://github.com/abus-aikorea/kara-audio or https://github.com/abus-aikorea/aria-coversong (from 2024.04.10)

Introduction

ABUS provides the latest AI tools with one click. We have the technology to install and run OpenAI's voice recognition & translation engine Whisper and Facebook Research's Demucs with one click. With ABUS One-Click, you can easily use the latest AI tools such as voice recognition, translation and vocal removal on your PC with one click, without complicated procedures such as system setup and model selection. Experience the latest AI technology faster than anyone else with ABUS One-Click.

ABUS One-Click Studio offers:

  • Supports system setup, installation, execution, and deletion processes with One-Click
  • 4-Tab interface
    • Studio Tab: YouTube downloader, vocal removal, automatic subtitle integrated environment
    • Downloader Tab: Download YouTube videos (mp4, webm). Supports image quality selection (low, good, best)
    • Splitter Tab: Vocal removal, Karaoke vidoe production. Supports 4 models of Demucs (htdemucs, htdemucs_ft, htdemucs_6s, mdx_extra). Supports 3 audio outputs (wav, flac, mp3)
    • Subtitle Tab: Voice recognition, automatic translation, automatic subtitles (srt, vtt, txt)

ABUS One-Click: Studio 실행 화면

Key-Features

  • Use yt-dlp to download YouTube videos.
  • You can download YouTube videos (mp4, webm) and save them as audio files (mp3, wav, flac).
  • Provides Demucs, a music source separation AI of Facebook Research.
  • Provides Whisper, a high-performance STT AI of OpenAI.
  • Once installed, it can be used permanently at no additional cost. ( ※ Free version has a 30-minute usage time limit)
  • Provides a Gradio Web-UI. I recommend the Google Chrome browser.
  • Supports over 90 languages including Japanese, Korean, English, Chinese, French and Spanish.

Running Environment

  • OS : Windows 10/11 (64bits) ※ Linux, Mac OS is not supported.
  • CPU: Intel Processor 2GHz or faster (or equivalent compatible)
  • RAM: 4GB or greater
  • HDD: At least 10GB of free space during installation
  • GPU: NVIDIA graphics card supporting CUDA 11.8 is recommended
  • Internet connection required (installation)

Installing and running

step 1. Package preparation

  • A. Paid version

    • Unzip the compressed file (abus-studio-v3.x.x.zip) included in the USB to an appropriate location on your computer.
    • Or, copy the already unzipped folder (abus-studio-v3.x.x) to an appropriate location on your computer.
  • B. Free version

    • Download and unzip the latest release ( Source code (zip) ) from GitHub Release
    • Or, download source code with git clone
git clone https://github.com/abus-aikorea/studio-free.git

step 2. How to install and run

  1. Run configure.bat: Install ffmpeg and CUDA (if using NVIDIA GPU) on Windows.
  2. Run start.bat: If ABUS One-Click is not installed, proceed with installation. Run Web-UI.
    • When the browser does not run automatically
      • Close the Windows-Commnad window and run start.bat again or
      • Run the browser directly and enter the address displayed in the Windows-Command window (e.g. http://127.0.0.1:11004 ) into the address bar.

step 3. How to uninstall

  • Run uninstall.bat: Remove installer_files . Remove the ffmepg and CUDA packages installed on Windows (if selected)

caution

When Windows Defender mistakenly recognizes a batch file as a Trojan, this is often called a 'False Positive'. To solve this problem, you can go through the following steps:

  1. File exception handling: In Windows Defender, you can set certain files or processes to skip security scanning. To do this, follow the steps below:
    • Click the ‘Start’ button and go to ‘Settings’.
    • Click ‘Update & Security’.
    • Select ‘Windows Security’ and go to ‘Virus & threat protection’.
    • Click ‘Manage Virus & Threat Protection Settings’.
    • Select 'Add exception' in 'Virus & threat protection settings'.
    • Select 'File or Folder', find the batch file in question and add it as an exception.
  2. Temporarily disable Windows Defender: This may be a temporary solution. However, you must be careful when using this method as it may expose your computer to other threats.
  3. Report the problem to anti-virus software: If you are sure that the file is not a Trojan horse, you can report it to Microsoft as a False Positive. Microsoft will review this and take any necessary action.

Contact us

YouTube

Copyright

by ABUS

studio-free's People

Contributors

abus-aikorea avatar

Stargazers

 avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar

Watchers

 avatar

studio-free's Issues

Features and Installation Concerns

This looks like a very interesting project. Thank you for sharing it.

I have a few questions, please:

  1. Does it support multiple languages, including right-to-left languages?
  2. What is the difference between the free and paid versions? And where can I obtain the paid version?
  3. When I tried to install it using configure.bat, it started downloading CUDA 11.8, and I had to stop it to ask if this will create a virtual environment or if it will affect my Windows packages. I currently have CUDA 12.2 installed and I do not want to change it, as other applications I use depend on it.
  4. Are there any documented steps for installing it using a virtual environment (venv)?

Looking forward to your answers.

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.