Add initial_prompt and hotwords support for Whisper transcription#25
Merged
Conversation
- Add initial_prompt and hotwords fields to TranscriptionConfig - Pass them via asr_options to whisperx.load_model() at model-load time - Expose --initial-prompt and --hotwords CLI flags - Document both options as commented examples in default config
paberr
approved these changes
Jun 2, 2026
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Problem
WhisperX exposes
initial_prompt(context priming) andhotwords(recognitionboosts for specific terms) via
asr_options, but ownscribe had no way to passthem through. Without them, recordings with product names, jargon, or non-English
proper nouns get silently mis-transcribed with no fix short of post-processing.
Solution
Expose both parameters via:
--initial-promptand--hotwordsinitial_promptandhotwordsunder[transcription]Both default to empty (no change to existing behaviour). When set, they are forwarded
to
whisperx.load_model()viaasr_options.One-off via CLI
ownscribe --initial-prompt "Acme Corp Q2 planning. Speakers: Alice, Bob."
--hotwords "ownscribe,WhisperX,pyannote"
Persistent via config
[transcription]
initial_prompt = "Weekly eng sync. Speakers: Alice, Bob, Carol."
hotwords = "ownscribe,WhisperX,pyannote"
Test plan
uv run pytest— all 230 tests passuv run ruff check src/ tests/— clean--initial-promptand--hotwordsappear inownscribe --helpwithout error
asr_optionsstays empty)