Fix confusing wording in the documentation (#2937)

Summary:
I have spent 2 hours because I read the documentation wrongly and trying to figure out why the I couldn't read the data from the dataset. The initial phrase was very confusing.

Pull Request resolved: https://github.com/pytorch/audio/pull/2937

Reviewed By: mthrok

Differential Revision: D42280738

Pulled By: nateanl

fbshipit-source-id: a48b9bc27d44ca8106bd56f805294a5a0e3ede1b

torchaudio/datasets/librimix.py

@@ -18,8 +18,8 @@ class LibriMix(Dataset):
     r"""*LibriMix* :cite:`cosentino2020librimix` dataset.
 
     Args:
-        root (str or Path): The path to the directory where the directory ``Libri2Mix`` or
-            ``Libri3Mix`` is stored.
+        root (str or Path): The path where the directory ``Libri2Mix`` or
+            ``Libri3Mix`` is stored. Not the path of those directories.
         subset (str, optional): The subset to use. Options: [``"train-360"``, ``"train-100"``,
             ``"dev"``, and ``"test"``] (Default: ``"train-360"``).
         num_speakers (int, optional): The number of speakers, which determines the directories