Transcribe and Summarize the Meeting Minutes with OpenAI Whisper and LangChain

In this guideline, I would like to share how I can transcribe and summarize the meeting minutes with Whisper and LangChain. For this to work, we need to record the meeting minutes and store the recording as an MP3 audio file.

I will be using an OpenAI Whisper, Azure OpenAI and LangChain.

Let’s install the Whisper either on our local machine or through Google Colab, as outlined in the GitHub repository mentioned.

GitHub - openai/whisper: Robust Speech Recognition via Large-Scale Weak Supervision

I’ll opt for Google Colab since my machine lacks a GPU.

Install whisper.

!pip install -U openai-whisper

Install ffmpeg.

!sudo apt update && sudo apt install ffmpeg