[Feat] Support PP-OCRv6 (#18104)

* Fix bugs

* Fix for python3.8

* Fix mcp server

* Optimize

* Fix bugs

* Refactor

* Fix MCP

* Bump MCP to 0.8.1

* Fix bugs

* Bump version to 0.8.2

* Fix bugs and update docs

* Update docs and fix bugs

* Fix bugs

* update pp-ocrv6

* update pp-ocrv6

# Conflicts:
#	docs/version3.x/module_usage/text_detection.md
#	docs/version3.x/module_usage/text_recognition.md
#	docs/version3.x/pipeline_usage/OCR.md
#	paddleocr/_api_client/models.py
#	paddleocr/_pipelines/ocr.py

* Bump paddleocr version

* update PP-OCRv6 docs: add model metrics, fix sizes, update language count to 50

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

* update PP-OCRv6: add model metrics/sizes to docs, support az/ku languages

- Add PP-OCRv6 model precision, sizes, descriptions to doc tables
- Add OCR pipeline introduction for PP-OCRv6
- Remove az/ku from unsupported latin langs (dict covers them)
- Update language count: 48->50 (medium/small), 47->49 (tiny)

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

* Change languages

* Bump js version

* add PP-OCRv6 English docs: algorithm doc + update model tables

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

* Use default model

* Update doc

* Update mcp docs

* update PP-OCRv6 algorithm docs and mkdocs nav: sync speed table with paper

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

* Support more params

* Fix MCP

* update READMEs and index docs: PP-OCRv5 -> PP-OCRv6 features

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

* Update sdk

* Fix bugs

* Fix unsaved

* Bump versions

* Fix bugs

* updata readme

---------

Co-authored-by: weixin_46524038 <weixin_46524038@noreply.gitcode.com>
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
Co-authored-by: zhangyubo0722 <zhangyubo0722@163.com>

Author: 4 people

README.md

@@ -44,9 +44,9 @@ English | [简体中文](./readme/README_cn.md) | [繁體中文](./readme/README
 ### 🔍 Universal Text Recognition (Scene OCR)
 > *The global gold standard for high-speed, multilingual text spotting.*
 
-* **100+ Languages Supported**: Native recognition for a vast global library. Our **PP-OCRv5** single-model solution elegantly handles multilingual mixed documents (Chinese, English, Japanese, Pinyin, etc.).
+* **100+ Languages Supported**: Native recognition for a vast global library. **PP-OCRv6** supports 50 languages with a single unified model (Chinese, English, Japanese, and 46 Latin-script languages) — no model switching needed for multilingual documents.
 * **Complex Element Mastery**: Beyond standard text recognition, we support **natural scene text spotting** across a wide range of environments, including IDs, street views, books, and industrial components
-* **Performance Leap**: PP-OCRv5 delivers a **13% accuracy boost** over previous versions, maintaining the "Extreme Efficiency" that PaddleOCR is famous for.
+* **Performance Leap**: PP-OCRv6 achieves **+4.6% detection** and **+5.1% recognition** accuracy over PP-OCRv5, surpassing mainstream Vision-Language Models. 5.2× CPU inference speedup end-to-end.
 
 <div align="center">
   <p>
@@ -62,14 +62,28 @@ English | [简体中文](./readme/README_cn.md) | [繁體中文](./readme/README
 
 ## 📣 Recent updates
 
-### 🔥 2026.05.28: Release of PaddleOCR 3.6.0
+### 🔥 2026.06.11: Release of PaddleOCR 3.7.0
+- PP-OCRv6 highlights:
+
+    - **Accuracy boost**: Medium tier achieves +4.6% detection and +5.1% recognition over PP-OCRv5_server, surpassing mainstream VLMs (Qwen3-VL-235B, GPT-5.5) with only 34.5M parameters.
+    - **50 languages unified**: Single model covers Chinese, English, Japanese, and 46 Latin-script languages — no model switching needed.
+    - **Specialized scenarios**: Major improvements in digital displays, dot-matrix characters, tire prints, and industrial text recognition.
+    - **Faster inference**: 5.2× CPU speedup (OpenVINO), 6.1× on Apple M4 (tiny), 0.13s on A100 GPU.
+    - **Three tiers for all scenarios**: tiny (1.5M) / small (7.7M) / medium (34.5M) for edge, mobile, and server deployment.
+    - **Documentation**: [PP-OCRv6 Technical Doc](https://paddlepaddle.github.io/PaddleOCR/latest/version3.x/algorithm/PP-OCRv6/PP-OCRv6.en.html)
+
+<details>
+<summary><strong>2026.05.28: Release of PaddleOCR 3.6.0</strong></summary>
+
 - PaddleOCR-VL-1.6 highlights:
 
     - **New SOTA Accuracy**: Achieves over 96.3% on OmniDocBench v1.6, also sets new SOTA on OmniDocBench v1.5 and Real5-OmniDocBench, leading both open-source and proprietary solutions in text, formula, and table recognition.
     - **Comprehensive Capability Upgrade**: Significant improvements in table, ancient document, and rare character recognition, with notably enhanced seal recognition, spotting, and chart understanding across multiple scenarios.
     - **Seamless Migration**: Model architecture is fully consistent with PaddleOCR-VL-1.5, enabling zero-cost adaptation—swap and go.
     - **Try it now**: Available on [HuggingFace](https://huggingface.co/PaddlePaddle/PaddleOCR-VL-1.6) or our [Official Website](https://www.paddleocr.com).
 
+</details>
+
 <details>
 <summary><strong>2026.04.21: Release of PaddleOCR 3.5.0</strong></summary>
 

api_sdk/README.md

@@ -37,7 +37,7 @@ Run these from the PaddleOCR repo root directory:
 
 ```bash
 # Python
-python -m pytest tests/test_api_client_http.py tests/test_api_client_core.py tests/test_api_client_resources.py
+python -m pytest tests/api_client/
 
 # TypeScript
 cd api_sdk/typescript

api_sdk/README_cn.md

@@ -35,7 +35,7 @@ Python SDK 是主 `paddleocr` 包的一部分。
 
 ```bash
 # Python
-python -m pytest tests/test_api_client_http.py tests/test_api_client_core.py tests/test_api_client_resources.py
+python -m pytest tests/api_client/
 
 # TypeScript
 cd api_sdk/typescript

api_sdk/go/README.md

@@ -43,6 +43,9 @@ if err != nil {
 fmt.Println(result.JobID, len(result.Pages))
 ```
 
+Set `Model: paddleocr.PPOCRv6` (or `"PP-OCRv6"`) to use the PP-OCRv6 hosted OCR model.
+Set `Model: paddleocr.PPOCRv5Latin` (or `"PP-OCRv5-latin"`) to use the PP-OCRv5 Latin-script hosted OCR model.
+
 Document parsing defaults to PaddleOCR-VL-1.6:
 
 ```go

api_sdk/go/README_cn.md

@@ -41,6 +41,9 @@ if err != nil {
 fmt.Println(result.JobID, len(result.Pages))
 ```
 
+将 `Model` 设为 `paddleocr.PPOCRv6`（或 `"PP-OCRv6"`）可使用 PP-OCRv6 云端 OCR 模型。
+将 `Model` 设为 `paddleocr.PPOCRv5Latin`（或 `"PP-OCRv5-latin"`）可使用 PP-OCRv5 拉丁语系云端 OCR 模型。
+
 文档解析默认使用 PaddleOCR-VL-1.6：
 
 ```go