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.

style_bert_vits2/models/utils/__init__.py

@@ -9,7 +9,6 @@ from typing import TYPE_CHECKING, Any, Optional, Union
 import numpy as np
 import torch
 from numpy.typing import NDArray
-from scipy.io.wavfile import read
 
 from style_bert_vits2.logging import logger
 from style_bert_vits2.models.utils import checkpoints  # type: ignore
@@ -162,6 +161,13 @@ def load_wav_to_torch(full_path: Union[str, Path]) -> tuple[torch.FloatTensor, i
         tuple[torch.FloatTensor, int]: 音声データのテンソルとサンプリングレート
     """
 
+    # この関数は学習時以外使われないため、ライブラリとしての style_bert_vits2 が
+    # 重たい scipy に依存しないように遅延 import する
+    try:
+        from scipy.io.wavfile import read
+    except ImportError:
+        raise ImportError("scipy is required to load wav file")
+
     sampling_rate, data = read(full_path)
     return torch.FloatTensor(data.astype(np.float32)), sampling_rate