PaddleOCR · Issues· 248 open

resize_norm_img 直接resize问题，宽高比大于10的数据丢弃代码怎么没找到呢

Error in "concatenate_markdown_pages" example in Usage tutorial for PPStructureV3: TypeError: write() argument must be str, not MarkdownResult

arabic_PP-OCRv5_mobile_rec: native aspect-ratio width under-allocates CTC steps for full-width lines (36.7% → 12.9% CER)

Broken documentation link in langchain-paddleocr/README.md

PP-OCRv6 训练可以使用图片高度为32的？对识别影响大？

PP-OCRv6/v5 unified rec ONNX 模型非 ASCII 输出为 CP1252 渲染的 UTF-8 字节（PP-OCRv6_small_rec_onnx）

结构化识别准确，但内容被合并到了一个block（疑似VL-1.6 新增，之前测试没有遇到）

NotImplementedError when using PaddleOCR 3.7.0 with PaddlePaddle 3.3.1

[PP-OCRv6][Performance] High CPU inference latency and low CPU utilization - need Small model accuracy with lower latency

PIR optimization does not yet support the Kunlun P800 server environment.

字符识别错误或者无法识别

识别不准确

PP-OCRv6 models are not registered in PaddleX when using PP-StructureV3 pipeline

ppocrv6 ">=" not supported between instance of 'list' and float

PP-OCRv5_server_rec outputs only zeros for Chinese text on Apple Silicon (ARM64) CPU