TechFoco Logo

OCR 专题

共 17 篇文章，按时间倒序展示。

Chandra OCR开源发布，具备强大功能和广泛应用潜力： - 支持完整版面信息解析，能识别并

Chandra OCR开源发布，具备强大功能和广泛应用潜力： - 支持完整版面信息解析，能识别并标注图片、图表 - 优秀的手写体、表格和表单识别能力 - 兼容transformers和vLLM架构，易于集成和扩展 获取方式： Huggingface仓库 | Github代码库 | 在线演示体验（推荐平衡模式） 通过Datalab API调用，支持balanced和accurate两种模式 快速上手： pip install chandra-ocr chandra_vllm chandra input.pdf ./output 性能与对比： - 在olmocr基准测试中优于Deepseek OCR，展现出更高准确率 - 相较Marker OCR，Chandra更擅长复杂格式和整体排版，但速度稍慢 - 支持多语言（基于Surya语言支持），但对部分低资源语言仍有提升空间 已知限制： - 纯数学公式识别尚不及Marker - 旋转页面识别准确度下降 - 部分低资源语言效果欠佳 未来计划： - 持续优化模型精度和性能 - 量化与加速支持，提升推理速度 - 扩展语言和用例覆盖

TechFoco
OCRDocument ParsingTransformers
Chandra OCR开源发布，具备强大功能和广泛应用潜力： - 支持完整版面信息解析，能识别并

olmOCR is an open-source tool designed for high-

olmOCR is an open-source tool designed for high-throughput conversion of PDFs and other documents into plain text while preserving natural reading order. It supports tables, equations, handwriting, and more. olmOCR has been trained on academic papers, technical documentation, and other reference content, and uses a unique prompting technique to increase accuracy and decrease hallucinations. For full details on the recipe, read our technical report. The current model was fine-tuned on English documents; other languages are not likely to work. Try the demo on your own documents below. You can then deploy the full olmOCR toolkit on your own GPUs for efficient, scalable document processing—at an estimated cost of just $190 USD per million pages converted.

TechFoco
OCRPDF conversionopen-source tool
olmOCR is an open-source tool designed for high-