more fixes

Author: lhoestq

datasets/caner/README.md

@@ -5,7 +5,8 @@ language_creators:
 - expert-generated
 languages:
 - ar
-licenses: []
+licenses:
+- unknown
 multilinguality:
 - monolingual
 size_categories:

datasets/chr_en/README.md

@@ -1,67 +1,38 @@
 ---
 annotations_creators:
-  monolingual:
-  - no-annotation
-  monolingual_raw:
-  - found
-  parallel:
-  - expert-generated
-  parallel_raw:
-  - expert-generated
+- expert-generated
+- found
+- no-annotation
 language_creators:
 - found
 languages:
-  monolingual:
-  - chr
-  - en
-  monolingual_raw:
-  - chr
-  parallel:
-  - chr
-  - en
-  parallel_raw:
-  - chr
-  - en
+- chr
+- en
 licenses:
 - other-different-license-per-source
 multilinguality:
-  monolingual:
-  - multilingual
-  monolingual_raw:
-  - monolingual
-  parallel:
-  - translation
-  parallel_raw:
-  - translation
+- monolingual
+- multilingual
+- translation
 size_categories:
-  monolingual:
-  - 100K<n<1M
-  monolingual_raw:
-  - 1K<n<10K
-  parallel:
-  - 10K<n<100K
-  parallel_raw:
-  - 10K<n<100K
+- 100K<n<1M
+- 10K<n<100K
+- 1K<n<10K
 source_datasets:
 - original
 task_categories:
-  monolingual:
-  - translation
-  monolingual_raw:
-  - text-generation
-  - fill-mask
-  parallel:
-  - translation
-  parallel_raw:
-  - translation
+- fill-mask
+- text-generation
+- translation
 task_ids:
-  monolingual: []
-  monolingual_raw:
-  - language-modeling
-  - masked-language-modeling
-  parallel: []
-  parallel_raw: []
+- language-modeling
+- masked-language-modeling
 paperswithcode_id: chren
+configs:
+- monolingual
+- monolingual_raw
+- parallel
+- parallel_raw
 ---
 
 # Dataset Card for ChrEn

datasets/mkb/README.md

@@ -24,100 +24,58 @@ annotations_creators:
 source_datasets:
 - original
 size_categories:
-  bn-en:
-  - 1K<n<10K
-  bn-gu:
-  - 1K<n<10K
-  bn-hi:
-  - 1K<n<10K
-  bn-ml:
-  - 1K<n<10K
-  bn-mr:
-  - 1K<n<10K
-  bn-or:
-  - n<1K
-  bn-ta:
-  - 1K<n<10K
-  bn-te:
-  - 1K<n<10K
-  bn-ur:
-  - n<1K
-  en-gu:
-  - 1K<n<10K
-  en-hi:
-  - 1K<n<10K
-  en-ml:
-  - 1K<n<10K
-  en-mr:
-  - 1K<n<10K
-  en-or:
-  - n<1K
-  en-ta:
-  - 1K<n<10K
-  en-te:
-  - 1K<n<10K
-  en-ur:
-  - 1K<n<10K
-  gu-hi:
-  - 1K<n<10K
-  gu-ml:
-  - 1K<n<10K
-  gu-mr:
-  - 1K<n<10K
-  gu-or:
-  - n<1K
-  gu-ta:
-  - 1K<n<10K
-  gu-te:
-  - 1K<n<10K
-  gu-ur:
-  - n<1K
-  hi-ml:
-  - 1K<n<10K
-  hi-mr:
-  - 1K<n<10K
-  hi-or:
-  - n<1K
-  hi-ta:
-  - 1K<n<10K
-  hi-te:
-  - 1K<n<10K
-  hi-ur:
-  - n<1K
-  ml-mr:
-  - 1K<n<10K
-  ml-or:
-  - n<1K
-  ml-ta:
-  - 1K<n<10K
-  ml-te:
-  - 1K<n<10K
-  ml-ur:
-  - n<1K
-  mr-or:
-  - n<1K
-  mr-ta:
-  - 1K<n<10K
-  mr-te:
-  - 1K<n<10K
-  mr-ur:
-  - n<1K
-  or-ta:
-  - n<1K
-  or-te:
-  - n<1K
-  or-ur:
-  - n<1K
-  ta-te:
-  - 1K<n<10K
-  ta-ur:
-  - n<1K
-  te-ur:
-  - n<1K
+- 1K<n<10K
+- n<1K
 licenses:
 - cc-by-4.0
 paperswithcode_id: null
 pretty_name: CVIT MKB
+configs:
+- bn-en
+- bn-gu
+- bn-hi
+- bn-ml
+- bn-mr
+- bn-or
+- bn-ta
+- bn-te
+- bn-ur
+- en-gu
+- en-hi
+- en-ml
+- en-mr
+- en-or
+- en-ta
+- en-te
+- en-ur
+- gu-hi
+- gu-ml
+- gu-mr
+- gu-or
+- gu-ta
+- gu-te
+- gu-ur
+- hi-ml
+- hi-mr
+- hi-or
+- hi-ta
+- hi-te
+- hi-ur
+- ml-mr
+- ml-or
+- ml-ta
+- ml-te
+- ml-ur
+- mr-or
+- mr-ta
+- mr-te
+- mr-ur
+- or-ta
+- or-te
+- or-ur
+- ta-te
+- ta-ur
+- te-ur
 ---
 
 # Dataset Card for CVIT MKB

datasets/myanmar_news/README.md

@@ -1,6 +1,8 @@
 ---
-annotations_creators: []
-language_creators: []
+annotations_creators:
+- found
+language_creators:
+- found
 languages:
 - my
 licenses:

datasets/norne/README.md

@@ -4,7 +4,7 @@ annotations_creators:
 language_creators:
 - crowdsourced
 languages:
-- false
+- "no"
 licenses:
 - other-national-library-of-norway
 multilinguality: