Using LLama2 to Correct OCR Errors
I've been disappointed by the very poor quality of results that I generally get when trying to run OCR on older scanned documents, especially ones that are typewritten or otherwise have unusual or irregular typography. I recently had the idea of using Llama2 to use common sense reasoning and subject level expertise to correct transcription errors in a "smart" way-- basically doing what a human proofreader who is familiar with the topic might do. I came up with the linked script that takes a PDF as input, runs Tesseract on it to get an initial text extraction, and then feeds this…
In plain words
This tool improves OCR accuracy on older scanned documents by combining Tesseract OCR with Llama2 AI. The script extracts text from PDFs, then uses Llama2 to correct transcription errors and format output as markdown, mimicking a human proofreader's expertise. It's designed for anyone frustrated with poor OCR results on typewritten or irregularly-formatted historical documents. The approach leverages modern Python libraries to make the process practical and accessible.
written from the facts on this page · September 2026
From the sources
In the maker’s words, at launch
I've been disappointed by the very poor quality of results that I generally get when trying to run OCR on older scanned documents, especially ones that are typewritten or otherwise have unusual or irregular typography. I recently had the idea of using Llama2 to use common sense reasoning and subject level expertise to correct transcription errors in a "smart" way-- basically doing what a human proofreader who is familiar with the topic might do. I came up with the linked script that takes a PDF as input, runs Tesseract on it to get an initial text extraction, and then feeds this sentence-by-sentence to Llama2, first to correct mistakes, and then again on the corrected text to format it as markdown where possible. This was surprisingly easier than I initially expected thanks to the very nice tooling now available in libraries such as llama-cpp-python, langchain, and pytesseract. But the big issue I was encountering was that Llama2 wasn't just correcting the text it was given-- it was also hallucinating a LOT of totally new sentences that didn't appear in the original text at all (some of these new sentences used words which never appeared elsewhere in the original text). I figured this would be pretty simple to filter out using fuzzy string matching-- basically check all the sentences in the LLM corrected text and filter out sentences that are very different from any sentences in the original OCRed text. To my surprise, this approach worked very poorly. In fact, lots of other similar tweaks, including using bag-of-words and the spacy NLP library in various ways (spacy worked very poorly in everything I tried). Finally I realized that I had a good solution staring me in the face: Llama2. I realized I could get sentence level vector embeddings straight from Llama2 using langchain. So I did that, getting embeddings for each sentence in the raw OCRed text and the LLM corrected text, and then computed the cosine similarity of each sentence in the LLM corrected text against all sentences in the raw OCRed text. If no sentences match in the raw OCRed text, then that sentence has a good chance of being hallucinated. In order to save the user from having to experiment with various thresholds, I saved the computed embeddings to an SQLite database so they only had to be computed once, and then tried several thresholds, comparing the length of the filtered LLM corrected text to the raw OCRed text; if things worked right, these texts should be roughly the same length. So as soon as the filtered length dips below the raw OCRed text length, it backtracks and uses the previous threshold as the final selected threshold. Anyway, if you have some very old scanned documents laying around, you might try them out and see how well it works for you. Do note that it's extremely slow, but you can leave it overnight and maybe the next day you'll have your finished text, which is better than nothing! I feel like this could be useful for sites like the Internet Archive-- I've found their OCR results to be extremely poor for older documents. I'm very open to any ideas or suggestions you might have. I threw this together in a couple days and know that it can certainly be improved in various ways. One idea that I thought might be fun would be to make this work with a Ray cluster, sending a different page of the document to each of the workers in the cluster to do it all at the same time.
More life & fun this month
the category →- TL
Life & fun · 10d ago · louisabraham.github.io
Photosynthesis fires two of your iPhone
Life & fun · 28d ago · photosynthesis.camera
SoloUno▲310Take control of hair pulling, nail biting & skin picking
Life & fun · 28d ago · solouno.io
Scroll through all 43,252,003,274,489,856,000 reachable Rubik's Cube permutations.
Life & fun · 26d ago · everycube.alen.is
Hi HN, I built Eigendrum, a web tool that solves the 2D wave equation for arbitrary shapes so you can hear what they sound like as drums. How it works: * Solves -∇²u = λu using finite element analysis (Kφ = λMφ) on a triangle mesh. * Validated to <0.1% error against closed-form solutions for circles (Bessel zeros) and rectangles. * Sound model factors in strike location, Rayleigh damping, and mallet width. * Includes Kac drums I & II to demonstrate identical sound spectra from different geometries. * No frameworks, build steps, or dependencies. Repo and tests:…
Life & fun · 26d ago · baselashraf81.github.io
Launched alongside, August 2023
the whole month →
Lottielab▲871Create and ship lottie animations to sites and apps faster
Dev tools · 2023 · lottielab.com
- LC
Outlines is a Python library that focuses on text generation with large language models. Brandon and I are not LLM experts and started the project a few months ago because we wanted to understand better how the generation process works. Our original background is probabilistic, relational and symbolic programming. Recently we came up with a fast way to generate text that matches a regex (https://blog.normalcomputing.ai/posts/2023-07-27-regex-guide...). The basic idea is simple: regular expressions have an equivalent Deterministic-Finite Automaton (DFA) representation. We…
AI · 2023 · github.com