Commit: d800960b511e3d229f0fee56f19372875ebb0189
Parent: 3ed2f45ff2a68f66982c28fb1d64829b2b877a21
Author: Randy Palamar
Date: Tue, 31 Jan 2023 19:45:37 -0700
ocr: update comment on trained data
Diffstat:
1 file changed, 3 insertions(+), 1 deletion(-)
diff --git a/bin/ocr b/bin/ocr
@@ -2,7 +2,9 @@
# copy text from an image to the clipboard
# deps: imagemagick tesseract slop xclip
-# you probably want the capture2text jpn file from here:
+# you probably want the jpn.traineddata or jpn_vert.traineddata from here:
+# https://github.com/tesseract-ocr/tessdata
+# or the capture2text one here:
# https://sourceforge.net/projects/capture2text/files/Dictionaries/Japanese.zip/download
TESS_DATA="$HOME/.local/share/tesseract"