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
3 Commits
Author SHA1 Message Date
diodiogod efe8d295d4 Update comments to explain PyTorch 2.9 bug fixes comprehensively 
- Clarify that global patch solves TWO issues: TorchCodec DLL + int16 normalization
- Explain timing criticality: patch must apply before torchaudio import
- Remove redundant pytorch_patches call from apply_all_compatibility_patches()
- Update save_audio_safe docstring to explain defense-in-depth approach
- Add detailed docstring to pytorch_patches explaining both issues and fixes
 2025-11-07 03:30:36 -03:00
diodiogod dff111889e Apply global PyTorch 2.9 TorchCodec monkey-patch at startup 
Recreate pytorch_patches.py with proper global monkey-patching of torchaudio.save/load
to use scipy.io.wavfile instead of TorchCodec. This fixes 'Could not load libtorchcodec'
errors on Windows with PyTorch 2.9.0+cu128 without needing fixes in every file.

Changes:
- Global monkey-patch applied at startup via comfyui_compatibility.py
- Works for ALL code that uses torchaudio.save/load (recorder, voice changer, etc)
- No user setup required, no FFmpeg workarounds needed
- Pure Python scipy solution, no native dependencies

This is the proper fix for TorchCodec Windows incompatibility with PyTorch 2.9.
 2025-11-07 03:11:33 -03:00
diodiogod cc544e9558 Version 4.10.9 
Fix Python 3.12 VRAM spikes with ComfyUI compatibility patch

Technical implementation:
- Add automatic CUDNN benchmark disabling for Python 3.12
- Implement compatibility patch system in utils/comfyui_compatibility.py
- Apply fix before TTS generation in unified text and SRT nodes
- Resolve ComfyUI v0.3.57+ regression affecting memory management
 2025-09-26 01:18:35 -03:00