I do this with just a prompt setting context of the meeting if we have it, explaining this is a spoken meeting between n people, and asking to correct based on the entire context, acutally works decently out of the box.
Damn, I just tried this with ChatGPT (warning: contrived example) and it works surprisingly well:
PROMPT:
The following is a partial transcription of a meeting at a tech company. Please correct any transcription errors, using clues from context as well as the fact that this is a technical meeting.
Person A: we shouldn't use a sequel database to store this data, we probably want to use something Callum nor instead since it's more efficient than row-based storage. Something like a patchy park or arrow.
Person B: What's park, eh?
Person A: It's just a column-based storage format with efficient Jesus or snappy compression.
RESPONSE:
Person A: "we shouldn't use a SQL database to store this data, we probably want to use something columnar instead since it's more efficient than row-based storage. Something like Apache Parquet or Arrow."
Person B: "What's Parquet?"
Person A: "It's just a column-based storage format with efficient GZIP or Snappy compression."
EDIT: mistral 7B on the other hand botched this terribly, and made up a lot of nonsense unrelated to the transcript.
