Fix ChatterBox SRT multiline segment routing and 23-Lang language tag switching
Technical details:
- Route Classic ChatterBox and ChatterBox Official 23-Lang multiline SRT subtitles through segmented generation
- Fix ChatterBox Official 23-Lang multilingual SRT processing to keep per-segment language tags like [pt:]
- Add generic pt alias so language-only Portuguese tags parse correctly
Add Vietnamese (Viterbox) community finetune support
Implementation details:
- Add Vietnamese (Viterbox) as model_version option for ChatterBox Official 23-Lang
- Support dolly-vn/viterbox repository with expanded Vietnamese tokenization (2549 tokens)
- Add flexible T3 model filename detection for community finetunes
- Add version normalization for file lookups and tokenizer selection
- Add Vietnamese language code mapping in language_mapper.py
- Fix vocab size detection by loading tokenizer before T3 model initialization
- Support 'as-is' format handling for mixed .pt/.safetensors community models
Add universal multilingual text preprocessing support
Implementation details:
- Add 📝 Phoneme Text Normalizer node with 4 processing methods
- Implement IPA phonemization using espeak backend
- Add Unicode decomposition for special characters
- Add cross-platform phonemizer support (Windows/Linux/Mac)
- Add F5-Polish model auto-download from reference implementation
- Improve multilingual F5-TTS pronunciation issues (refs #22, #54, #58)
- Add Polish language support with high-quality model integration
Implement complete SRT subtitle processing for IndexTTS-2 engine with:
- Character switching with emotion references using existing parser
- Full SRT timing support (stretch_to_fit, pad_with_silence, smart_natural, concatenate)
- Pause tag support with emotion control
- Language mapping integration for multilingual support
- Unified interface integration following VibeVoice pattern
Key components:
- IndexTTSSRTProcessor: Clean SRT processor using existing IndexTTSProcessor
- Language mapper support: Added index_tts engine type with multilingual handling
- Unified SRT node integration: Added IndexTTS-2 to unified TTS SRT interface
- Add Italian to CHATTERBOX_MODELS registry with unified_model special flag
- Implement _load_unified_model() method for Italian checkpoint format
- Italian model uses single chatterbox_italian_final.pt with all components
- Load base architecture then replace with fine-tuned Italian weights
- Support bilingual Italian/English with [it] language prefix
- Extended vocabulary: 1500 tokens (704 frozen English + 796 trainable Italian)
- Update language mapper for Italian language code 'it' -> 'Italian'
- Based on deployment script analysis from niobures repository
Usage: Italian text requires '[it]' prefix, English text uses no prefix
- Add special tokenizer filename handling for Japanese (tokenizer_jp.json) and Korean (tokenizer_en_ko.json)
- Mark French model as incomplete (only has t3_cfg.safetensors)
- Update model requirements validation for incomplete models
- Fix dynamic tokenizer discovery in TTS loading
- Ensure all niobures language models have correct file expectations
- Remove duplicate alias definitions (character_parser already handles this)
- Map canonical language codes to ChatterBox models efficiently
- Support natural language tags: [USA:], [Deutschland:], [France:], [Russia:]
- Enable ChatterBox-specific model variants: [de-best:], [de-expressive:]
- Unified alias system now works across F5-TTS and ChatterBox engines
Users can now use natural language switching:
- [USA:John] Hello → English model
- [Deutschland:Hans] Hallo → German model
- [France:Marie] Bonjour → French model
- [Russia:Ivan] Привет → Russian model
- [de-best:Klaus] Das beste Modell → German (havok2) model
Implemented complete VibeVoice SRT processor with dual mode support:
Features:
• Native Multi-Speaker Mode: One segment per subtitle using VibeVoice's Speaker 1:, Speaker 2: format
• Custom Character Switching Mode: Multiple segments per subtitle (one per character)
• Full SRT timing support: stretch_to_fit, pad_with_silence, smart_natural, concatenate
• Modular architecture using existing utils (no code duplication)
• Character switching with voice discovery integration
• Pause tag support in both modes
• Smart language grouping and model switching
Technical Implementation:
• Added VibeVoiceSRTProcessor with complete SRT workflow
• Updated unified SRT node to support vibevoice engine
• Added VibeVoice to language_mapper utility
• Proper ComfyUI audio format handling
• Fixed timing adjustment format for detailed reports
Integration:
• Uses existing timing utils, audio assembly, and reporting modules
• Compatible with Character Voices node
• Maintains same interface as ChatterBox/F5-TTS SRT nodes
Root cause: WorkItem dataclass missing critical fields causing streaming workers to use hardcoded defaults instead of user parameters.
Key fixes:
- Add missing fields to WorkItem: seed, enable_audio_cache, crash_protection_template, device
- Update worker inputs to use WorkItem fields instead of hardcoded values
- Fix WorkItem creation to populate all fields from original inputs
- Remove local: prefix handling in language_mapper for consistency
- Add comprehensive language normalization in character_parser
- Comment out verbose cache debug logs while keeping success messages
Now both traditional (batch_size=0) and streaming (batch_size=3) modes generate identical cache keys with same parameters, ensuring proper cache hits and avoiding duplicate processing.
Streaming parallelization system now fully functional with cache consistency.
- Language mapper now passes through local models (e.g., 'local:German') directly
- Character parser handles ChatterBox language codes properly vs F5-TTS model names
- This should fix narrator segments using correct main language selection
Remove IndicF5-Hindi model support due to architecture incompatibility
IndicF5 uses custom transformer layers incompatible with F5-TTS DiT architecture.
Model weights cannot be loaded due to different layer structure (time_embed.time_mlp,
text_embed.text_blocks vs standard F5-TTS layers).
- Removed IndicF5Engine and all references
- Updated language mappings to fall back to base F5TTS models
- F5-Hindi-Small remains available as Hindi TTS alternative
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.
- Language mapper was hardcoding English to F5TTS_v1_Base regardless of engine config
- Now respects engine's configured model for English when it's an English model
- Prevents unnecessary model switching during character switching
- Engine configured with F5TTS_Base will now stay on F5TTS_Base for English characters
- Maintains fallback to F5TTS_v1_Base for non-English default models
diodiogod