This page lists repositories with Tesseract4 compatible tessdata (for --oem 1 - LSTM) by Tesseract community.
Such tessdata contributions should ideally document everything needed to reproduce the training process (fonts, images, ground truth, texts, scripts, documentation, ...).
| Language Code | Language | Data File | Contributor | Info |
|---|---|---|---|---|
| khmLimon | Khmer | best | OpenInstituteCambodia/phyrumsk | PR in tessdata_best |
| cop | Coptic | best | shreeshrii/tessdata_coptic | tesseract-ocr forum post |
| jpn_vert | Japanese Vertical | best | zodiac3539/jpn_vert | tesseract-ocr forum post |
| ocrb_plus | MRZ | best | shreeshrii/tessdata_ocrb | tesseract-ocr forum post |
| jav_java | Aksara Jawa | best | Shreeshrii/tessdata_jav_java | tesseract-ocr forum post |
| mrz | MRZ | best | DoubangoTelecom/tesseractMRZ | tesseract-ocr forum post |
| dot_matrix | MRZ | best | ameera3/OCR_Expiration_Date | tesseract-ocr forum post |
| e13b | E13B (or MICR) | best | ElMagoElGato/tess_e13b_training | tesseract-ocr forum post |
| e13b | E13B (or MICR) | best | DoubangoTelecom/tesseractMICR | tesseract-ocr forum post |