Repository navigation
Add experimental room-tone synthesis and opt-in repair fallback - #2
Draft
lobsterclause wants to merge 1 commit into
Draft
lobsterclause wants to merge 1 commit into
lobsterclause wants to merge 1 commit into
Conversation
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Stack
Stacked on draft #1 (
feat/dialogue-leveller), not directly on main. This PR adds only the room-tone work; merge/release is not requested.Summary
opendubstage roomtone, reproducible seeds, JSON reports, strict timing validation and input/output collision guards.specrepair --synthesize-tonefallback when no contiguous candidate meets the existing minimum length/context constraints. Existing defaults are unchanged; untouched PCM samples remain exact.Verification
make verify: 206 tests passed locally (Linux, Python 3.12).git diff --checkclean.Limitations
Experimental mono only; explicit timings/clean selections, no VAD. Slow modulation preserves approximate depth, not the original trajectory or modulation spectrum. Narrow tonal hum and strongly nonstationary sources are not guaranteed. Runtime/memory scale with requested duration. Synthetic checks do not replace listening validation; no listening validation or release claim.