Skip to content

Support streaming swda dataset #4914

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

Merged
merged 2 commits into from
Aug 30, 2022
Merged

Support streaming swda dataset #4914

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
79a7e8a
Support streaming swda dataset
albertvillanova Aug 30, 2022
d2b63f6
Remove unused import
albertvillanova Aug 30, 2022
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
10 changes: 4 additions & 6 deletions datasets/swda/swda.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -26,7 +26,6 @@
import csv
import datetime
import glob
import io
import os
import re

Expand Down Expand Up @@ -435,10 +434,8 @@ def _split_generators(self, dl_manager):
dl_dir = dl_manager.download_and_extract(_URL)
# Use swda/ folder.
data_dir = os.path.join(dl_dir, "swda")
# Handle partitions files.
urls_to_download = self._URLS
# Download extract and return paths of split files.
downloaded_files = dl_manager.download_and_extract(urls_to_download)
# Handle partitions files: download extract and return paths of split files.
downloaded_files = dl_manager.download(self._URLS)

return [
# Return whole data path and train splits file downloaded path.
Expand Down Expand Up @@ -476,7 +473,8 @@ def _generate_examples(self, data_dir, split_file):
"""

# Read in the split file.
split_file = io.open(file=split_file, mode="r", encoding="utf-8").read().splitlines()
with open(file=split_file, mode="r", encoding="utf-8") as f:
split_file = f.read().splitlines()
# Read in corpus data using split files.
corpus = CorpusReader(src_dirname=data_dir, split_file=split_file)
# Generate examples.
Expand Down