- Implement proper streaming model pre-loading with StreamingModelManager
- Fix character alias resolution in voice discovery system
- Add crash protection to streaming workers
- Fix TTS model loading in traditional mode
- Simplify unified UI by removing confusing batch processing toggles
- Ensure voice_refs maps both original and resolved character names
- Add centralized language mapping for streaming multilingual support
Streaming now works correctly with proper voice assignments and language switching.
- Add character_grouper.py: Groups segments by character within each language
- Add batch_processor.py: Handles batch processing and sequential fallback
- Add T3.batch_inference(): True simultaneous batch processing for T3 model
- Update ChatterBox TTS engine with improved generate_batch() method
- Update node to use modular character grouping system
FIXED: Character grouping now works perfectly - segments with same character
are properly grouped together (e.g., crestfallen_original segments 3,5,7,13...
are now grouped instead of processed separately).
Architecture: Language grouping (existing) -> Character grouping (new) -> Batch processing
Files are modular and under 500 lines for LLM optimization.
Note: Character grouping works, but batch processing condition needs investigation.
diodiogod