Update README.md

README.md

@@ -5,5 +5,5 @@ this is ja cc filter for reference from ja wiki vs random ja common crawl, and b
 3. get pure text and remove content len less than 1k,
 4. use langdetect to tell the lang of the pages, we finally get total 101K ja pages
 5. random sample from commoncrawl 202303 and use langdetect to find 101k ja pages
-6. tokenize all text with "cl-tohoku/bert-base-japanese"
+6. tokenize all text with "rinna/japanese-roberta-base"
 7. feed tokens to fasttext to get model.bin