Upload a .wav file to your Google Drive that is a recording of a meeting. The Colab notebook will transcribe it using OpenAI Whisper, identify all speakers using pyannote.audio, and save two csv files: transcript.csv which has all speakers and what they're saying in sequential time, and speakers.csv which has the statistics of who speaks how much (and how fast). You need to give it a huggingface token (get your own on huggingface.co). Add the question you want answered about the meeting and copy and paste transcript.csv into ChatGPT. To download the generated csv files, click on the Files icon on the left of the notebook and download them from there.
-
Notifications
You must be signed in to change notification settings - Fork 4
Google Colab notebook which will take in an audio file, transcribe it using OpenAI Whisper, identify all speakers using pyannote.audio, and make the full marked up transcript available for passing into an LLM for querying.
marioschlosser/meeting-gpt
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
Folders and files
Name | Name | Last commit message | Last commit date | |
---|---|---|---|---|
Repository files navigation
About
Google Colab notebook which will take in an audio file, transcribe it using OpenAI Whisper, identify all speakers using pyannote.audio, and make the full marked up transcript available for passing into an LLM for querying.
Resources
Stars
Watchers
Forks
Releases
No releases published
Packages 0
No packages published