Tadahito Yao

Implementation for PyTorch is here. It's working very well. https://github.com/davda54/sam

Issue is still present in Japanese recognition. I investigated with latest master(12e0fb4e015bac1be5076d65d01aab9856ce0e98) of tesseract and following image.  With latest tessdata_best: (Spaces between every tokens) ``` 種々 の 帳票 文書...

`preserve_interword_spaces` is written in only jpn_vert.config and not in jpn.config, `preserve_interword_spaces` should be written in jpn.config as well. https://github.com/tesseract-ocr/langdata/blob/master/jpn/jpn.config https://github.com/tesseract-ocr/langdata/blob/master/jpn_vert/jpn_vert.config

Does `tessedit_load_sublangs jpn_vert` work like `#include` ? According to the OCR result in https://github.com/tesseract-ocr/tesseract/issues/2702#issuecomment-877776874 `preserve_interword_spaces` in config seems not working or ignored. The command line I used is: `tessreact sample.png...

Same problem occurred to me. My workaround is to remove empty lines from training_text. It worked for me.

In my understanding linuxbrew cannot run any GUI applications. Is latest linuxbrew able to do that? Or any past version of PC6001VX worked on linuxbrew?

I tried to make homebrew environment and installed PC6001VX bottle. It looks xcb plugin is not included in qt6 bottle. ``` $ QT_QPA_PLATFORM_PLUGIN_PATH=~/homebrew/share/qt/plugins/platforms QT_QPA_PLATFORM=wayland ~/homebrew/bin/PC6001VX Failed to create wl_display (No...

INSTALL.mdの記載に従ったらビルドできました。 README.mdに記載の手順が古いという問題だったようです。

this may help. https://takao0616.hatenablog.com/entry/2019/02/20/220133

src/Qt以外のソースは、原則上流のPC6001Vのものなので、原作者の方に連携しておきます。 Qt依存のコードやマクロも、src/Qt以外では使わないことになっています。