feat: add v2 post-correct mode with optional local llm
This commit is contained in:
@@ -160,3 +160,11 @@ The project now features a high-performance, Apple Silicon-optimized pipeline th
|
||||
- Wrapped Arabic caption content in explicit RTL embedding marks for better bidirectional layout stability.
|
||||
- Added punctuation normalization for Arabic display (`،`, `؛`, `؟`) to reduce LTR punctuation artifacts.
|
||||
- **Outcome:** Arabic captions render more consistently in terminal output, especially when adjacent to English/French/Spanish caption lines.
|
||||
|
||||
## Phase 20: Post-Correct Mode (V2 Foundation)
|
||||
- **Goal:** Add a practical second-stage correction pass for finalized English captions.
|
||||
- **Approach:**
|
||||
- Added `--post-correct` mode to run deterministic rule-based cleanup after ASR (spacing, punctuation cleanup, disfluency reduction, immediate duplicate-word collapse).
|
||||
- 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.
|
||||
|
||||
Reference in New Issue
Block a user