Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Fix Windows paths in SUPERB benchmark datasets #3009

Merged
merged 1 commit into from
Oct 4, 2021
Merged

Fix Windows paths in SUPERB benchmark datasets #3009

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
16 changes: 8 additions & 8 deletions datasets/superb/superb.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -430,7 +430,7 @@ def _split_generators(self, dl_manager):
def _generate_examples(self, archive_path, split=None):
"""Generate examples."""
if self.config.name == "asr":
transcripts_glob = os.path.join(archive_path, "LibriSpeech", "*/*/*/*.txt")
transcripts_glob = os.path.join(archive_path, "LibriSpeech", "*", "*", "*", "*.txt")
key = 0
for transcript_path in sorted(glob.glob(transcripts_glob)):
transcript_dir_path = os.path.dirname(transcript_path)
Expand Down Expand Up @@ -462,8 +462,8 @@ def _generate_examples(self, archive_path, split=None):
label = "_unknown_"
yield key, {"file": audio_file, "label": label}
elif self.config.name == "ic":
root_path = os.path.join(archive_path, "fluent_speech_commands_dataset/")
csv_path = os.path.join(root_path, f"data/{split}_data.csv")
root_path = os.path.join(archive_path, "fluent_speech_commands_dataset")
csv_path = os.path.join(root_path, "data", f"{split}_data.csv")
with open(csv_path, encoding="utf-8") as csv_file:
csv_reader = csv.reader(csv_file, delimiter=",", skipinitialspace=True)
next(csv_reader)
Expand All @@ -478,7 +478,7 @@ def _generate_examples(self, archive_path, split=None):
"location": location,
}
elif self.config.name == "si":
wav_path = os.path.join(archive_path, "wav/")
wav_path = os.path.join(archive_path, "wav")
splits_path = os.path.join(archive_path, "veri_test_class.txt")
with open(splits_path, "r", encoding="utf-8") as f:
for key, line in enumerate(f):
Expand Down Expand Up @@ -518,9 +518,9 @@ def _generate_examples(self, archive_path, split=None):
}
key += 1
elif self.config.name == "er":
root_path = os.path.join(archive_path, f"Session{split}/")
wav_path = os.path.join(root_path, "sentences/wav/")
labels_path = os.path.join(root_path, "dialog/EmoEvaluation/*.txt")
root_path = os.path.join(archive_path, f"Session{split}")
wav_path = os.path.join(root_path, "sentences", "wav")
labels_path = os.path.join(root_path, "dialog", "EmoEvaluation", "*.txt")
emotions = ["neu", "hap", "ang", "sad", "exc"]
key = 0
for labels_file in sorted(glob.glob(labels_path)):
Expand Down Expand Up @@ -653,7 +653,7 @@ def _get_speakers(rec, data, args):


def _split_ks_files(archive_path, split):
audio_path = os.path.join(archive_path, "**/*.wav")
audio_path = os.path.join(archive_path, "**", "*.wav")
audio_paths = glob.glob(audio_path)
if split == "test":
# use all available files for the test archive
Expand Down