From d60d1e6bceade9c55f3623558f1af5548bd4c65f Mon Sep 17 00:00:00 2001 From: Gabriel Date: Fri, 16 Sep 2022 09:46:07 -0400 Subject: [PATCH] Add variant column --- README.rst | 1 + src/corporacreator/corpora.py | 1 + 2 files changed, 2 insertions(+) diff --git a/README.rst b/README.rst index aaa07ef..55f8ef6 100644 --- a/README.rst +++ b/README.rst @@ -107,6 +107,7 @@ The ``clips.tsv`` file is a `tab separated file`_ containing a dump of the raw d 6) ``age`` - The age range of the contributor, if the contributor reported it 7) ``gender`` - The gender of the contributor, if the contributor reported it 8) ``accents`` - The accent of the contributor, if the contributor reported it +8) ``variant`` - The variant of the language that contributor speaks, if the contributor reported it 9) ``locale`` - The locale describing the language the contributor was reading 10) ``bucket`` - The "bucket" (train, dev, or test) the clip is currently assigned to diff --git a/src/corporacreator/corpora.py b/src/corporacreator/corpora.py index 563d10a..b9a80c5 100644 --- a/src/corporacreator/corpora.py +++ b/src/corporacreator/corpora.py @@ -66,6 +66,7 @@ def create(self): "age", "gender", "accents", + "variant", "locale", "segment" ]