# Regression with reading the CMU ARCTIC dataset

**URL:** <https://discuss.pytorch.org/t/regression-with-reading-the-cmu-arctic-dataset/224243>\
**Category:** audio\
**Created:** [December 22, 2025, 12:40pm UTC](https://discuss.pytorch.org/t/regression-with-reading-the-cmu-arctic-dataset/224243 "2025-12-22T12:40:06Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![rhdunn](https://discuss.pytorch.org/user_avatar/discuss.pytorch.org/rhdunn/32/78969_2.png) [@rhdunn](https://discuss.pytorch.org/u/rhdunn)\
**Post date:** [December 22, 2025, 12:40pm UTC](https://discuss.pytorch.org/t/regression-with-reading-the-cmu-arctic-dataset/224243/1 "2025-12-22T12:40:06Z")

</div>

The commit to fix Python 3.13 support has resulted in a regression in reading the text of the CMU ARCTIC dataset for entries that contain a comma as commit [Fix datasets/cmuarctic test failures when using python 3.13 (#4071) · pytorch/audio@7d4c0bf · GitHub](https://github.com/pytorch/audio/commit/7d4c0bf04035b36bad0565e7d6eddfc5208bab28) switched from using `\n` as the column delimiter to the default `,` delimiter.

Bug Report with the details: [The CMUARCTIC dataset yields the wrong text transcripts · Issue #4161 · pytorch/audio · GitHub](https://github.com/pytorch/audio/issues/4161)