Skip to content

Simple web application, which can be used to convert and translate audio to subtitles by OpenAI's Whisper model

License

Notifications You must be signed in to change notification settings

cuxs/whisper-website

 
 

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

51 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Website which convert speech to text by Whisper model (Official Repo)

This is an adaptation from https://github.com/Kabanosk/whisper-website/

Added:

  • Max character per subtitle
  • Option to translate

Hosting website on localhost:

  1. Clone the repo - git clone git@github.com:Kabanosk/whisper-website.git
  2. Go to repo directory - cd whisper-website
  3. Create virtual environment - python3 -m venv venv
  4. Activate the environment - source venv/bin/activate/. venv/bin/activate
  5. Install requirements - pip install -r requirements.txt
  6. Go to src directory - cd src
  7. Run the run.py file - python3 run.py
  8. Go to your browser and type http://127.0.0.1:8000/ if the browser doesn't open

Run website on localhost with Docker

First time

  1. Install Docker
  2. Clone the repo - git clone git@github.com:Kabanosk/whisper-website.git
  3. Go to repo directory - cd whisper-website
  4. Create Docker image - docker build -t app .
  5. Run Docker container - docker run --name app_container -p 80:80 app
  6. Go to your browser and type http://127.0.0.1:80/

Next time

  1. Start your Docker container - docker start app_container
  2. Go to your browser and type http://127.0.0.1:80/

About

Simple web application, which can be used to convert and translate audio to subtitles by OpenAI's Whisper model

Resources

License

Code of conduct

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • Python 47.6%
  • HTML 33.3%
  • JavaScript 11.7%
  • CSS 2.8%
  • Dockerfile 2.4%
  • Batchfile 1.2%
  • Shell 1.0%