Commit Graph
8 Commits
Author SHA1 Message Date
diodiogod 4a4df30db8 Disable old auto-phonemization system
The old auto-phonemization system is now disabled in favor of the
dedicated 📝 Phoneme Text Normalizer node which gives users full control.

Changes:
- Modified should_use_phonemization() to always return False
- Added deprecation notice explaining the replacement
- Users now have explicit control via the Phoneme Text Normalizer node

This prevents unexpected automatic phonemization and respects the
auto_phonemization=False setting properly.
2025-09-23 01:19:03 -03:00
diodiogod 256a5de28e Version 4.9.6
Fix ChatterBox Official 23-Lang language resolution and narrator input

Technical details:
- Fix resolve_language_alias AttributeError across multiple engines
- Fix ChatterBox Official 23-Lang not using opt_narrator audio input
- Fix phonemizer_utils language alias resolution method call
- Fix character_parser validation module language resolution
2025-09-16 19:54:18 -03:00
diodiogod 118b7df7cc Add Italian to F5-TTS phonemization exceptions
- Add 'it' to models_to_skip list alongside PT-BR
- Update debug message to reflect both Portuguese and Italian models
- Update PROJECT_INDEX.md with phonemizer utilities documentation

Italian F5-TTS models work better with native text rather than IPA phonemization,
similar to Portuguese-Brazil models.
2025-09-06 14:13:34 -03:00
diodiogod 9bb80c06b6 Version 4.8.12
Fix F5-TTS auto_phonemization toggle not working

Technical details:
- Fix parameter missing from unified TTS text node call
- Add auto_phonemization parameter to F5TTS API chain
- Fix F5TTS wrapper not passing parameter to inference
- Add parameter to infer_process and infer_batch_process
- Fix cache invalidation with proper parameter flow
- Remove debug messages when phonemization disabled
2025-09-06 13:43:11 -03:00
diodiogod 6eac6e377a Version 4.8.11
Import wildminder VibeVoice improvements

Technical improvements:
- Add Blackwell RTX 50 series SageAttention support (SM120+)
- Enhance input validation to prevent NaN/Inf tensor corruption
- Improve audio preprocessing with better extreme value handling
- Add post-resampling validation to catch library artifacts

Note: Transformers 4.56+ compatibility was already implemented.
2025-09-06 12:32:32 -03:00
diodiogod d526f41089 Version 4.8.9
Fix ChatterBox Official 23-Lang safetensors support

Technical implementation:
- Add smart loading logic preferring official .pt files
- Support user safetensors with strict=False compatibility mode
- Implement download fallback from .pt to safetensors format
- Add proper missing file detection and re-download logic
- Fix file format validation in download checker
2025-09-06 10:56:28 -03:00
diodiogod 86c2546258 Version 4.8.8
Fix F5-TTS multilingual phonemization system

Technical implementation:
- Add auto_phonemization UI toggle to F5-TTS Engine node
- Implement smart phonemization detection with user control
- Disable phonemization for F5-PT-BR (confirmed to worsen quality)
- Add experimental warnings for multilingual model testing
- Ensure phonemization flows through SRT and regular TTS workflows
- Add cache separation for different phonemization settings
2025-09-06 09:33:09 -03:00
diodiogod c23930912a Version 4.8.7
Fix ChatterBox transformer compatibility issue

Technical changes:
- Set attention implementation to eager mode
- Fix output_attentions conflict with sdpa in transformers 4.36+
- Maintain alignment analyzer functionality
2025-09-06 08:38:08 -03:00