Skip to content

Latest commit

 

History

History
79 lines (51 loc) · 2.33 KB

README.md

File metadata and controls

79 lines (51 loc) · 2.33 KB

Transcription Service

This Python-based service allows you to transcribe audio files using Google Cloud Speech-to-Text, generate summaries and meeting minutes with OpenAI's text-davinci-003, and manage files using Google Cloud Storage.

Features

  • Audio transcription from .mp4 and .m4a files.
  • Conversion of audio to .wav format.
  • Generation of summaries and meeting minutes.
  • Uploading, managing, and deleting files on Google Cloud Storage.

Requirements

  • Python 3.7+
  • Google Cloud SDK
  • openai
  • pydub
  • textwrap
  • google-cloud-speech
  • google-cloud-storage
  • concurrent.futures

Installation

  1. Install the required Python packages with pip:
pip install google-cloud-speech google-cloud-storage pydub openai
  1. Clone the repository:
git clone https://github.com/davidtsui1/transcription_service.git
  1. Navigate to the project directory:
cd transcription_service

  1. Set up your Google Cloud and OpenAI configurations:

    • For Google Cloud, follow the instructions here.
    • For OpenAI, follow the instructions here.

  2. Replace 'YOUR_PROJECT_ID' and 'YOUR_BUCKET_NAME' in the transcription_service.py file with your actual project ID and bucket name.

Usage

python transcription_service.py

Contributing

Pull requests are welcome. For major changes, please open an issue first to discuss what you would like to change.

License

This project is licensed under the MIT License. See the MIT License file for details.

Dependencies

This project makes use of the following third-party libraries, which have their own licenses:

Please refer to the respective license links for more details.

About the Author

This Transcription Service project was developed by David Rich Tsui. You can find more about him and his work on his GitHub profile.