add wikipedia

piskvorky · Nov 10, 2017 · 0a5437a · 0a5437a
1 parent ad161d5
commit 0a5437a
Showing 1 changed file with 10 additions and 0 deletions.
diff --git a/list.json b/list.json
@@ -1,5 +1,15 @@
 {
 	"corpora": {
+		"wiki-en": {
+			"description": "Extracted Wikipedia dump from October 2017. Produced by `python -m gensim.scripts.segment_wiki -f enwiki-20171001-pages-articles.xml.bz2 -o wiki-en.gz`",
+			"checksum-0": "a7d7d7fd41ea7e2d7fa32ec1bb640d71",
+			"checksum-1": "b2683e3356ffbca3b6c2dca6e9801f9f",
+			"checksum-2": "c5cde2a9ae77b3c4ebce804f6df542c2",
+			"checksum-3": "00b71144ed5e3aeeb885de84f7452b81",
+			"file_name": "wiki-en.gz",
+			"source": "https://dumps.wikimedia.org/enwiki/20171001/",
+			"parts": 4
+		},
 		"text8": {
 			"description": "Cleaned small sample from wikipedia",
 			"checksum": "68799af40b6bda07dfa47a32612e5364",