Skip to content
Trending storyDeveloping

Docling v2.149.0 adds MiniCPM-OCR preset for PDF processing

1 article1 sourcesince Nov 9Last article 1h ago ·

Overview

AISummary of 1 article

Docling v2.149.0 adds a minicpm_ocr preset for OpenBMB's 1.3B MiniCPM-OCR model, which handles English and Chinese text, according to OpenBMB. Users can run it on one consumer GPU with the command docling doc.pdf --pipeline vlm --vlm-model minicpm_ocr.

The release also adds an opt-in --use-embedded-picture-images flag and ASR support on mlx-audio. It fixes the --vlm-model flag so that it switches to the VLM pipeline.

Written by AI from the articles below · updated Nov 9, 8:45 PM ET

Check the sources:

Latest developmentNov 9, 8:40 PM ET
Docling v2.149.0 adds MiniCPM-OCR preset for PDF processing

Article timeline

The articles in this story. Times are ET.

Nov 9
  1. OpenBMBOfficial
    Docling v2.149.0 adds MiniCPM-OCR preset for PDF processing

    AIDocling v2.149.0 adds a minicpm_ocr preset for OpenBMB's 1.3B MiniCPM-OCR model, which handles English and Chinese text. Users can run it on one consumer GPU with docling doc.pdf --pipeline vlm --vlm-model minicpm_ocr. The release also adds an opt-in --use-embedded-picture-images flag and ASR support on mlx-audio, and fixes the --vlm-model flag, which now switches to the VLM pipeline.

Heat Trend

Not enough continuous observations to show a trend yet.