fix(config): register parakeet-cpp as a transcript backend (#9718)#10106
Merged
mudler merged 1 commit intoMay 31, 2026
Merged
Conversation
parakeet-cpp was added in mudler#10084 but not registered in BackendCapabilities, so GuessUsecases only allowed "whisper" for FLAG_TRANSCRIPT and the UI could not classify parakeet-cpp models as speech-to-text. The result was that parakeet models appeared only in the LLM selector in the speech-to-speech pipeline, making them unusable for transcription through the UI. Closes mudler#9718 Assisted-by: Claude Sonnet 4.6 <noreply@anthropic.com>
4 tasks
mudler
approved these changes
May 31, 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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
Fixes #9718 — after installing a parakeet model, the speech-to-speech pipeline UI only offers it in the LLM selector, not the speech-to-text selector.
Root cause:
parakeet-cppwas added in #10084 but never registered inBackendCapabilities.GuessUsecases(model_config.go:798) only allows"whisper"forFLAG_TRANSCRIPT, so any backend not in the capabilities map is gated out of the transcript usecase by the heuristic fallback. All other STT backends (faster-whisper,whisperx,moonshine,nemo,qwen-asr,voxtral) are registered in the map and bypass that guard.Fix: Add a
"parakeet-cpp"entry toBackendCapabilitieswithMethodAudioTranscription/UsecaseTranscript, matching the pattern of every other STT backend in the same block.Test plan
gofmt -eon the edited file: clean🤖 Generated with Claude Code