- Fixed engine initialization issue where adapter never called initialize_engine
- Fixed model configuration key mismatch (generation_repo vs generation_model)
- Fixed tokenizer download file name (model.pth vs pytorch_model.bin)
- Fixed tensor dimension issues for ComfyUI audio output format
- Added comprehensive multi-speaker mode system with three options:
* Custom Character Switching: Use [Alice], [Bob] with character voice files
* Native Multi-Speaker (System Context): Use [SPEAKER0], [SPEAKER1] with opt_second_narrator
* Native Multi-Speaker (Conversation): Same as above but conversation history mode
- Removed audio_priority widget, now follows standard TTS priority logic
- Fixed mode selection bug where config was read from wrong object
- Added proper audio format handling for Character Voices in native modes
- Fixed pause tag support in all modes including native multi-speaker
- Improved tooltips to clarify mode requirements and text formats
Major Features:
• Added F5-Hindi-Small (632MB) and IndicF5-Hindi (1.4GB) models with auto-download
• Added support for 11 Indian languages: Hindi, Assamese, Bengali, Gujarati, Kannada, Malayalam, Marathi, Odia, Punjabi, Tamil, Telugu
• Added flexible Small model architecture detection (768 dim, 18 layers) vs Base (1024 dim, 22 layers)
• Enhanced fallback directory support: models/F5-TTS/ (primary) and models/Checkpoints/F5-TTS/ (fallback)
Architecture Improvements:
• Replaced hardcoded language detection with dynamic language mapper integration
• Added flexible model size detection for any future Small variants (155M params)
• Fixed language switching logic to only switch on explicit [lang:character] tags
• Added comprehensive Indian language aliases with native scripts
Bug Fixes:
• Fixed model loading errors for Hindi models using correct step numbers and file paths
• Fixed language switching detection to check original text instead of processed segments
• Fixed Small model architecture mismatch (18 vs 22 layers) with proper config detection
• Updated README with accurate model sizes and new Hindi options
Technical Details:
• F5-Hindi-Small: SPRINGLab/F5-Hindi-24KHz, model_2500000.safetensors, F5TTS_Small config
• IndicF5-Hindi: AI4Bharat/IndicF5, model.safetensors, supports 11 Indian languages
• Enhanced language_mapper.py with all 11 Indian languages pointing to appropriate models
• Improved character_parser.py with dynamic language inference from models
- Implement generic local-first fallback utility for all TTS engines
- Fix ChatterBox and F5-TTS duplicate model loading during language fallback
- Add F5-TTS language grouping to load models once per language group
- Fix pt-br language mapping support in language mapper
- Add model tracking to prevent redundant loading in multilingual engine
- Optimize SRT nodes to use unified language-grouped processing
This ensures efficient model loading with proper local model reuse,
eliminating unnecessary downloads and duplicate model loading for
low-VRAM scenarios while maintaining full language support.
diodiogod