Tigrigna Resources about langdata

[zmeharen]

Hi Shreeshrii,

I have been working on improving Tesseract's ability to recognize Tigrinya (ti or tir) language from PDF and other image files. I have noticed a few errors and I have been working on training the software. I have been working on it for about a week. Thank you for posting the link it has helped me in finding the resources I need. If you need help with this language let me know. I might need some guidance or direction but I will do what I can to help. Thank You,

Z

[Shreeshrii]

Thanks. Please share the errors that you have noticed, since @theraysmith is retraining all the languages, and your feedback may help improve this language's recognition. - excuse the brevity, sent from mobile On 24-Feb-2017 6:15 PM, "zmeharen" <[email protected]> wrote: Hi Shreeshrii, I have been working on improving Tesseract's ability to recognize Tigrinya (ti or tir) language from PDF and other image files. I have noticed a few errors and I have been working on training the software. I have been working on it for about a week. Thank you for posting the link it has helped me in finding the resources I need. If you need help with this language let me know. I might need some guidance or direction but I will do what I can to help. Thank You, Z — You are receiving this because you authored the thread. Reply to this email directly, view it on GitHub <#49 (comment)>, or mute the thread <https://github.com/notifications/unsubscribe-auth/AE2_o__AFKg6I4elg2X7tZI8tJRAf41Zks5rftDpgaJpZM4L3Jiy> .

[Shreeshrii]

tesseract-ocr/tesseract#654 (comment)

@theraysmith commented 2 days ago
Update: after going back to the www to get fresh data, I believe that my corpus text is now good for:
chr
dzo
iku
snd
syr
tgk
tir
I have put a lot of time into cleaners/filters for languages that use 'virama' characters.
I am not convinced that they are perfect, but I will add the code to the github repo in due course, so experts/native speakers can offer suggestions/fixes to make them better.