Built to provide insight into media content.
Explore the docs »
Report Bug
·
Request Feature
File Insights is a tool that takes a media file (.wav, .mp3, .mp4, .pdf, or .png) and provides further information regarding the file's content. We use machine learning, natural language processing, and web-scraping to provide succinct, translated summaries of Wikipedia articles relevant to the file. We've implemented NLP algorithms to extract named entitites and summarize text, so users can quickly learn more about major topics. We use an image captioning ML model to caption images that don't have any text and we use
the textract library for every other file type. All of these features (and more!) are integrated into an easy-to-use Flask website.
- Python
- Tensorflow
- NLTK
- Beautiful Soup
- Flask
To get a local copy up and running, follow these simple steps.
-
Verify if python (Version >= 3.8) is installed. Previous versions may also work.
python --version
- If not, go to https://www.python.org/downloads.
- If not, go to https://www.python.org/downloads.
-
Verify if pip is installed
pip --version
- Clone the repo
git clone https://github.com/dgobalak/File-Insights.git
- Create a virtual environment
python -m venv venv
- Activate the virtual environment
venv\scripts\activate
- Install dependencies
pip install -r requirements.txt
- Start the Flask app
python run.py
Contributions are what make the open source community such an amazing place to learn, inspire, and create. Any contributions you make are greatly appreciated.
- Fork the Project
- Create your Feature Branch
git checkout -b AmazingFeature
- Commit your Changes
git commit -m 'Add some AmazingFeature'
- Push to the Branch
git push origin AmazingFeature
- Open a Pull Request and wait for it to be reviewed.
Distributed under the Apache 2.0 License . See LICENSE
for more information.
- Daniel Gobalakrishnan - [email protected]
- Project Link: https://file-insights.herokuapp.com
-
Icons made by Freepik from www.flaticon.com