4 posts tagged with "experiment"

I diffed the EasyOCR and Qwen3-VL transcriptions of 444 Soviet cookbook pages against each other, and the two engines produced character-for-character identical text on only 5 pages. All 5 are nearly blank (a heading or a page number, 13 to 24 characters each). The plan from the previous post was to treat pages where both engines agree as "probably accurate" and hand-check only the rest. On real content pages that agreement almost never happens, so cross-engine agreement doesn't work as the cheap accuracy filter I hoped for.

Docling's vision-language model pipeline, running the 4B-parameter Qwen3-VL model locally, processed 444 cookbook page images for the soviet.recipes project at a 99.5% success rate. Compared to the earlier EasyOCR run, it gave up every piece of debugging output that run had: no text-region overlays, no per-page confidence score, no reading-order artifacts. It also ran far slower, and Docling still processes one-page image documents one at a time, so the batch took about 26.3 hours.

An AMD Ryzen AI Max+ 395 laptop with its integrated Radeon 8060S GPU and unified memory can run open-weight models from 4B parameters up to a 120B mixture-of-experts model, no cloud GPU needed. gpt-oss-120b generates around 35-40 tokens per second, and the 20B and 4B models are faster still. That's enough for the soviet.recipes project: this hardware can host a model large enough to attempt vision-language OCR locally.

Two HP ZBook units arrived damaged from shipping in a row: the first had a cracked screen, and its replacement had a screw missing from the cover. Two for two isn't the batting average anyone wants from a laptop. I ordered the ZBook with 128GB of RAM to run local AI inference experiments, and to replace an old laptop that was dying.