Refactor: remove dependencies on libraries not required for style_bert_vits2 as a library

librosa: Originally not used under style_bert_vits2/.
pyannote.audio: Required only when using the "infer style vector from audio" function during inference, but it is currently almost unused.
scipy: Because it was used in only one utility function that was not needed outside of training.

pyproject.toml

@@ -26,18 +26,15 @@ dependencies = [
     'cn2an',
     'g2p_en',
     'jieba',
-    'librosa==0.9.2',
     'loguru',
     'num2words',
     'numba',
     'numpy',
-    'pyannote.audio>=3.1.0',
     'pydantic>=2.0',
     'pyopenjtalk-dict',
     'pypinyin',
     'pyworld-prebuilt',
     'safetensors',
-    'scipy',
     'torch>=2.1',
     'transformers',
 ]