31–37 of 37 posts
We recently published a cookbook for constrained decoding here: https://nanonets.com/cookbooks/structured-llm-outputs/
Earlier quoted context omitted.
Ocrbase is CUDA only while dots.ocr uses vLLM, so should support ROCm/AMD cards?
How about CPU?
There is a pipeline solution with multiple small specific models that can run only with CPU: https://github.com/RapidAI/RapidOCR
Earlier quoted context omitted.
How about CPU?
dots.ocr requires requires a considerable amount of computational resources. If you have Mac device with ARM CPU(M series), you can try my dots.ocr.runner( https://github.com/jason-ni/app.dots.ocr.runner ). There is a pipeline solution with multiple small specific models that can run only with CPU: https://github.com/RapidAI/RapidOCR
Earlier quoted context omitted.
I fought with Tesseract for quite a while. Its good if high accuracy doesn't matter. Transcribing a book from clean, consistent non-skewed data its fine and an LLM might even be able to clean it up. But for legal or accounting data from hand scanned documents, the error rate made it untenable. Even clean, scanned documents of the same category have all sorts of density and skew anomalies that get misinterpreted. You'…
Thanks. I was surprised that Tesseract had recognized poorly scanned magazines and with some Python library I was able to transcribe two-columns layout with almost no errors. Tesseract is a cheap solution as it doesn’t touch any LLM. For invoices, Gemini flash is really good, for sure, and you receive “sorted” data as well. So definitely thumbs up. I use it for transcription of difficult magazine layout. I think that…