Update bundled IndexTTS-2 to latest upstream version
Technical implementation:
- Sync with https://github.com/index-tts/index-tts commits 8336824..64cb31a
- Add normalize_emo_vec() function from commit 8aa8064 for voice identity protection
- Add _load_and_cut_audio() helper from commit 0828dcb for 15s audio truncation
- Add persistent cache clearing from commit 64cb31a with torch.cuda.empty_cache()
- Fix BigVGAN CUDA kernel import path from commits ee23371, e409c4a
- Enhance emotion vector logging for better user feedback
diodiogod
b24bd37897