adolforeyna/whisper-translation
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

feat: add optional llm merge-decider for smart caption revisions

Browse Source
This commit is contained in:
Adolfo Reyna
2026-03-06 19:56:07 -05:00
parent 564fcaac1a
commit 2881bd96dd
2 changed files with 89 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files
history.md
+8
View File
@@ -168,3 +168,11 @@ The project now features a high-performance, Apple Silicon-optimized pipeline th
- Added optional local LLM correction via Ollama (`--post-correct-llm`, model/url/timeout flags) with strict fallback to rules-only when unavailable.
- Integrated post-correction after bridge-to-English and before downstream translation so improved English text propagates to target-language MT.
- **Outcome:** The pipeline now supports a two-stage transcription flow (ASR -> correction) with low-latency defaults and optional local generative enhancement.
## Phase 21: LLM Merge-Decider for Line Revisions
- **Goal:** Improve English line-merge quality when smart-correct revision is ambiguous.
- **Approach:**
- Added optional `--llm-merge-decider` to validate/refine heuristic merge candidates using the local post-correct LLM.
- Enforced strict low-latency behavior with `--llm-merge-timeout` (default 0.7s) and automatic fallback to heuristic merges on errors/timeouts.
- Added safety guards to reject overly large LLM rewrites and preserve buffered caption state when merge is rejected.
- **Outcome:** Merge decisions remain fast and deterministic by default, with optional LLM arbitration for cleaner sentence continuity.