Raising RuntimeErrors when datasets missing (#2430)

Summary:
Checks download flag and raises error when dataset is missing given download flag exists. Unit tested manually.

edit: Changed path to check as well as comment that is returned.

Pull Request resolved: https://github.com/pytorch/audio/pull/2430

Reviewed By: carolineechen

Differential Revision: D36815729

Pulled By: skim0514

fbshipit-source-id: f062db7919271665b88ec9754d85cfa83b4f6fa3

torchaudio/datasets/cmuarctic.py

@@ -120,7 +120,12 @@ class CMUARCTIC(Dataset):
                     checksum = _CHECKSUMS.get(url, None)
                     download_url_to_file(url, archive, hash_prefix=checksum)
                 extract_archive(archive)
-
+        else:
+            if not os.path.exists(self._path):
+                raise RuntimeError(
+                    f"The path {self._path} doesn't exist. "
+                    "Please check the ``root`` path or set `download=True` to download it"
+                )
         self._text = os.path.join(self._path, self._folder_text, self._file_text)
 
         with open(self._text, "r") as text:

torchaudio/datasets/libritts.py

@@ -122,6 +122,12 @@ class LIBRITTS(Dataset):
                     checksum = _CHECKSUMS.get(url, None)
                     download_url_to_file(url, archive, hash_prefix=checksum)
                 extract_archive(archive)
+        else:
+            if not os.path.exists(self._path):
+                raise RuntimeError(
+                    f"The path {self._path} doesn't exist. "
+                    "Please check the ``root`` path or set `download=True` to download it"
+                )
 
         self._walker = sorted(str(p.stem) for p in Path(self._path).glob("*/*/*" + self._ext_audio))
 

torchaudio/datasets/ljspeech.py

@@ -60,6 +60,12 @@ class LJSPEECH(Dataset):
                     checksum = _RELEASE_CONFIGS["release1"]["checksum"]
                     download_url_to_file(url, archive, hash_prefix=checksum)
                 extract_archive(archive)
+        else:
+            if not os.path.exists(self._path):
+                raise RuntimeError(
+                    f"The path {self._path} doesn't exist. "
+                    "Please check the ``root`` path or set `download=True` to download it"
+                )
 
         with open(self._metadata_path, "r", newline="") as metadata:
             flist = csv.reader(metadata, delimiter="|", quoting=csv.QUOTE_NONE)

torchaudio/datasets/speechcommands.py

@@ -109,6 +109,12 @@ class SPEECHCOMMANDS(Dataset):
                     checksum = _CHECKSUMS.get(url, None)
                     download_url_to_file(url, archive, hash_prefix=checksum)
                 extract_archive(archive, self._path)
+        else:
+            if not os.path.exists(self._path):
+                raise RuntimeError(
+                    f"The path {self._path} doesn't exist. "
+                    "Please check the ``root`` path or set `download=True` to download it"
+                )
 
         if subset == "validation":
             self._walker = _load_list(self._path, "validation_list.txt")

torchaudio/datasets/tedlium.py

@@ -108,6 +108,12 @@ class TEDLIUM(Dataset):
                     checksum = _RELEASE_CONFIGS[release]["checksum"]
                     download_url_to_file(url, archive, hash_prefix=checksum)
                 extract_archive(archive)
+        else:
+            if not os.path.exists(self._path):
+                raise RuntimeError(
+                    f"The path {self._path} doesn't exist. "
+                    "Please check the ``root`` path or set `download=True` to download it"
+                )
 
         # Create list for all samples
         self._filelist = []