Every weight is -1, 0 or +1, packed four to a byte. The model reads a 32-pixel-tall text strip and emits characters through CTC, decoded with a prefix beam search over a 27 KB character language model. It is more accurate than Tesseract 5 on degraded text and on fonts, ties on clean documents, and returns noticeably fewer perfect lines. Full numbers and the reasons are below, including where it loses. Reproduce with python3 benchmarkvstesseract.py. Ground truth needs no hand labelling: a digital PDF already contains its own exact text, so rasterizing a page and cropping each line at the bbox the PDF reports gives pixels whose correct answer is known. Training and test documents are split by…
Independent publisher
Raymond Gonzalez
psikosen
Models in Library1
Datasets in Library0
Models on Hugging Face18
Followers1
Compare the published evidence
This profile connects the 1 model and dataset record shown below to their upstream cards and sources. The library counts describe SAVRN's coverage, rather than this publisher's entire output.
Published tasks: Image to text.
Reported licenses: mit. Open a record to review its specific license and conditions.
Compare model specifications, source dates, and hardware estimates on the individual records. Publisher identity verification is separate from a model's quality, deployment readiness, or suitability for your work.