nodes/diodiogod-TTS-Audio-Suite
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity
1,649 Commits 25 Branches 22 Tags
codex/audio-cpp-integration
Commit Graph
6 Commits
Author SHA1 Message Date
diodiogod 51e97f70f6 Version 4.14.34 
Fix RVC HuBERT subdirectory double-nesting issue

Technical fix:
- Add check to detect if .pt file is already in correct subdirectory
- Prevent creating nested subdirectories (e.g., chinese_hubert_base/chinese_hubert_base/)
- Use existing subdirectory path when model is already correctly placed
 2025-12-02 09:54:53 -03:00
diodiogod 4214491e59 Version 4.14.32 
Fix RVC HuBERT model loading and compatibility

Technical changes:
- Fix Japanese HuBERT download URL (moved to public prj-beatrice repo)
- Fix content-vec-best model reference (was hubert-base-rvc)
- Add transformers HuBERT support with TransformersHubertWrapper
- Implement subdirectory structure for transformers models to avoid config conflicts
- Add auto-migration for existing models to new subdirectory structure
- Fix HubertConfig import scope issue in loaders.py
- Add config.json auto-download for transformers models
- Fix dtype conversion (float16/float32) in feature extraction
- Add dimension mismatch detection with helpful user messages
- Fix hubert_path parameter passthrough in conversion pipeline
 2025-12-02 00:41:24 -03:00
diodiogod eaf5123bd9 Version 4.11.7 
Fix RVC HuBERT model loading error

Technical details:
- Add direct .pt loading attempt before safetensors conversion
- Improve error handling for unsupported model formats
- Add fallback mechanism for complex fairseq models
 2025-10-13 09:09:35 -03:00
diodiogod 3e5f9a3721 Fix RVC Python 3.13 compatibility - comprehensive numba/librosa solution 
Major compatibility overhaul for RVC engine in Python 3.13 environments:

🔧 Core Compatibility Fixes:
• Disabled numba JIT compilation for Python 3.13+ via environment variables
• Added comprehensive librosa compatibility patches for missing functions:
  - pad_center, tiny (as function), fill_off_diagonal, is_positive_int, expand_to
• Replaced librosa.resample with torchaudio.resample to eliminate numba dependency
• Fixed all relative imports in RVC implementation (. notation)

⚡ Performance Improvements:
• Manual RMS calculation replacing librosa.feature.rms (avoids numba)
• Higher quality audio resampling using torchaudio
• Maintains backward compatibility with Python 3.12

🐛 Bug Fixes:
• Fixed 'function' object has no attribute 'get_call_template' errors
• Resolved 'float' object is not callable in librosa.sequence.viterbi
• Fixed ImportError for missing librosa utility functions
• Enhanced error handling and debugging throughout RVC pipeline

✨ Features:
• Comprehensive monkey-patching system for librosa compatibility
• Automatic fallbacks for failed operations
• Detailed logging for troubleshooting

Successfully tested with full RVC voice conversion workflow in Python 3.13.6.
 2025-09-06 17:22:33 -03:00
diodiogod 30da2ba370 Version 4.3.7: Fix TTS Audio Suite model organization and RVC Hubert compatibility issues 2025-08-13 13:43:14 -03:00
diodiogod df5996e4e7 Finalize SCNet implementation with experimental warning 
- Keep SCNet as experimental due to audio buzzing artifacts
- Add clear warnings in CLI and UI tooltips about quality issues
- Implementation functionally complete with chunked processing
- Users warned about potential audio artifacts before use
 2025-08-08 13:39:20 -03:00