[docs] minor fix (#1439)

* [docs] minor fix * validate cuts of UnsupervisedWaveformDataset
lhotse-speech · Dec 19, 2024 · 509f4a9 · 509f4a9
1 parent 9bd2071
commit 509f4a9
Show file tree

Hide file tree

Showing 2 changed files with 3 additions and 1 deletion.
diff --git a/docs/datasets.rst b/docs/datasets.rst
@@ -41,7 +41,7 @@ A typical Lhotse's dataset API usage might look like this:
     from lhotse.dataset import K2SpeechRecognitionDataset, SimpleCutSampler
 
     cuts = CutSet(...)
-    dset = K2SpeechRecognitionDataset(cuts)
+    dset = K2SpeechRecognitionDataset()
     sampler = SimpleCutSampler(cuts, max_duration=500)
     # Dataset performs batching by itself, so we have to indicate that
     # to the DataLoader with batch_size=None

diff --git a/lhotse/dataset/unsupervised.py b/lhotse/dataset/unsupervised.py
@@ -65,6 +65,8 @@ def __init__(self, collate: bool = True) -> None:
         self.collate = collate
 
     def __getitem__(self, cuts: CutSet) -> Dict[str, Any]:
+        self._validate(cuts)
+
         if self.collate:
             audio, audio_lens = collate_audio(cuts)
             return {