Add parsing pipeline section to model card

Add a 'Parsing pipeline' subsection under Model architecture describing the two-stage pipeline (PP-DocLayoutV3 layout detection in the SDK environment + region recognition over HTTP to a MiniCPM-OCR 1.0 inference service), with a new assets/parsing_pipeline.svg diagram. Supersedes #13: updates the SDK name to minicpm-ocr and unifies spelling.

README.md

@@ -130,12 +130,12 @@ Original documents and parsed results, side by side.
 
 ### Parsing pipeline
 
-Full-page parsing runs as a **two-stage pipeline** orchestrated by the [`minicpmvocr` SDK](https://pypi.org/project/minicpm-ocr/). The two stages use separate models, run in separate environments, and may run on different machines:
+Full-page parsing runs as a **two-stage pipeline** orchestrated by the [`minicpm-ocr` SDK](https://pypi.org/project/minicpm-ocr/). The two stages use separate models, run in separate environments, and may run on different machines:
 
 - **Stage 1 — Layout detection (SDK environment).** The PP-DocLayoutV3 layout model detects document regions — text, tables, formulas, charts, seals — and determines reading order; the SDK crops each region. It runs locally inside the SDK environment and requires PaddlePaddle / PaddleX.
 - **Stage 2 — Region recognition (inference service).** The SDK sends each cropped region over HTTP to a MiniCPM-OCR 1.0 inference service — served by vLLM, SGLang, llama.cpp, or Ollama — with a prompt matching the region type, then assembles the recognized content into the final Markdown / JSON in reading order.
 
-<p align="center"><img src="assets/parsing_pipeline.svg" alt="Parsing pipeline: in the minicpmvocr SDK environment, the PP-DocLayoutV3 layout model detects and crops document regions; each cropped region is sent over HTTP to a separate recognition service running MiniCPM-OCR 1.0 (vLLM, SGLang, llama.cpp, or Ollama); the SDK then assembles the recognised text, tables, formulas, charts, and seals into Markdown and JSON in reading order." width="90%"></p>
+<p align="center"><img src="assets/parsing_pipeline.svg" alt="Parsing pipeline: in the minicpm-ocr SDK environment, the PP-DocLayoutV3 layout model detects and crops document regions; each cropped region is sent over HTTP to a separate recognition service running MiniCPM-OCR 1.0 (vLLM, SGLang, llama.cpp, or Ollama); the SDK then assembles the recognized text, tables, formulas, charts, and seals into Markdown and JSON in reading order." width="90%"></p>
 
 See the [model guide](https://github.com/OpenBMB/MiniCPM-OCR/blob/main/docs/minicpm_ocr_1dot0_en.md) for more on architecture, parsing workflow,
 deployment options, and benchmark breakdowns.