Transcriptor is a web application that generates a quick summary and analyzes sentiment for videos/audios using advanced Natural Language Processing techniques.

• Fast: Transcriptor helps you save over 70% of your time by quickly providing a summary to highlight key points from videos/audios
• Easy: A simple and friendly web interface is provided used to summarize videos/audios
• Powerful: Transcriptor uses TensorFlow libraries to get highly accurate summaries in no time

Installation :: Demo Website :: License :: Contributions :: Future Scope :: Contributors :: Support

1. Clone the Git repository and cd into the new repo

git clone https://github.com/secheaper/transcriptor.git
cd transcriptor

2. This project uses Python 3, so make sure that Python and Pip are preinstalled. All requirements of the project are listed in the requirements.txt file. Use pip to install all of those

pip install -r requirements.txt

3. Once all the requirements are installed, you will have to cd into the source folder. Once in the source folder, use the streamlit command to run the transcriptor.py file

cd source
streamlit run transcriptor.py

4. If all went well, you should see the Network URL where this application is running on your local computer

The project is deployed on Streamlit Cloud

• Streamlit

This project is licensed under the terms of the MIT license. Please check License for more details.

Please see our CONTRIBUTING.md for instructions on how to contribute to the project by completing some of the issues.

For enhancement of this project following functionalities can be implemented

• Currently our application supports .wav audios, youtube videos and videos with .mp4 extension. Provide support for other video and audio formats
• Perform summarization for videos/audios in languages other than English
• Provide summary in form of video
• Generate summary of videos/audios for specific time frames
• Compare various Summarization models and provide optimal summary
• Adding Chrome extension for Transcriptor
• Develop a Discord BOT for transcriptor

We would like to thank Dr. Timothy Menzies for helping us understand the process of building a good Software Engineering project. We would also like to thank the teaching assistants Xiao Ling, Andre Lustosa, Kewen Peng, Weichen Shi for their support throughout the project. Also thanks to the amazing teams at Streamlit, Huggingface and Shields.io for their amazing projects!

Shubham Mankar

Pratik Devnani

Moksh Jain

Rahil Sarvaiya

Anushi Keswani

For any queries and help, please reach out to us at: [email protected]