PaddleOCR/latest/version3.x/pipeline_usage/OCR

[giscus[bot]]

PaddleOCR/latest/version3.x/pipeline_usage/OCR

Awesome multilingual OCR toolkits based on PaddlePaddle (practical ultra lightweight OCR system, support 80+ languages recognition, provide data annotation and synthesis tools, support training and deployment among server, mobile, embedded and IoT devices)

https://paddlepaddle.github.io/PaddleOCR/latest/version3.x/pipeline_usage/OCR.html

[PaoloP-creator]

/Users/home/Downloads/汤用彤 - 汉魏两晋南北朝佛教史 2.pdf OCR

[PaoloP-creator]

Can you OCR a File?

[PaoloP-creator]

/Users/home/Downloads/汤用彤 - 汉魏两晋南北朝佛教史 2.pdf

[AngieTLYang]

I need to align my image's resolution (dpi) and dimensions (width & height pixels) with the demo image, general_ocr_002.png, so that it works.

[436and251]

虽然你这里声明ocr.predict是结果列表，但是如果走的piepline那个逻辑，predict产生的output却是generator

[HighLordA]

你好，我在使用最新cpu 的orc版本 ，使用单例模式的话第一次成功 第二次必然会失败 第三次就会成功 这样往复的 似乎是有资源没释放使用完

[zhangyubo0722]

PaddleOCR 3.1 has been released, featuring the new PP-OCRv5 multilingual text recognition model. It supports 37 languages including French, Spanish, Portuguese, Russian, Korean, and more, achieving an average recognition accuracy improvement of over 30%. Welcome to try it out!

[zwbc-zcz]

模型路径中为什么不能包含中文

[436and251]

ocr实例化的好像可以，走pipeline的好像就不能包含中文，我也遇到了。

[zwbc-zcz]

PaddleOcr实例化也是不能包含中文 ***@***.***> 在 2025年7月10日 周四 10:19 写道： ocr实例化的好像可以，走pipeline的好像就不能包含中文，我也遇到了。 — Reply to this email directly, view it on GitHub, or unsubscribe. You are receiving this because you commented.

[WXWXwqz]

paddleocr ocr -i https://paddle-model-ecology.bj.bcebos.com/paddlex/imgs/demo_image/general_ocr_002.png
信息: 用提供的模式无法找到文件。
C:\Users\gggad\AppData\Local\Programs\Python\Python311\Lib\site-packages\paddle\utils\cpp_extension\extension_utils.py:715: UserWarning: No ccache found. Please be aware that recompiling all source files may be required. You can download and install ccache from: https://github.com/ccache/ccache/blob/master/doc/INSTALL.md
warnings.warn(warning_message)
Creating model: ('PP-LCNet_x1_0_doc_ori', None)
Using official model (PP-LCNet_x1_0_doc_ori), the model files will be automatically downloaded and saved in C:\Users\gggad.paddlex\official_models.
Creating model: ('UVDoc', None)
Using official model (UVDoc), the model files will be automatically downloaded and saved in C:\Users\gggad.paddlex\official_models.
Creating model: ('PP-LCNet_x1_0_textline_ori', None)
Using official model (PP-LCNet_x1_0_textline_ori), the model files will be automatically downloaded and saved in C:\Users\gggad.paddlex\official_models.
Creating model: ('PP-OCRv5_server_det', None)
Using official model (PP-OCRv5_server_det), the model files will be automatically downloaded and saved in C:\Users\gggad.paddlex\official_models.
Creating model: ('PP-OCRv5_server_rec', None)
Using official model (PP-OCRv5_server_rec), the model files will be automatically downloaded and saved in C:\Users\gggad.paddlex\official_models.
Connecting to https://paddle-model-ecology.bj.bcebos.com/paddlex/imgs/demo_image/general_ocr_002.png ...
Downloading general_ocr_002.png ...
[==================================================] 100.00%
[2025/08/03 10:55:48] paddleocr INFO: Processed item 0 in 522.8934288024902 ms
{'res': {'input_path': 'C:/Users/gggad/.paddlex/predict_input/general_ocr_002.png', 'page_index': None, 'model_settings': {'use_doc_preprocessor': True, 'use_textline_orientation': True}, 'doc_preprocessor_res': {'input_path': None, 'page_index': None, 'model_settings': {'use_doc_orientation_classify': True, 'use_doc_unwarping': True}, 'angle': 270}, 'dt_polys': array([], dtype=float64), 'text_det_params': {'limit_side_len': 64, 'limit_type': 'min', 'thresh': 0.3, 'max_side_limit': 4000, 'box_thresh': 0.6, 'unclip_ratio': 1.5}, 'text_type': 'general', 'text_rec_score_thresh': 0.0, 'rec_texts': [], 'rec_scores': array([], dtype=float64), 'rec_polys': array([], dtype=float64), 'rec_boxes': array([], dtype=float64)}} 我这个demo运行完了没有任何识别结果，这是什么问题呢？

[joey-bing-614]

每次使用，都必须初始化一次ocr吗，因为我发现把ocr放在函数外面的话，每次调用接口，第一次都成功，第二次都会失败。

[dengLG]

请问文本检测需要区分语种吗？对应使用不同的模型吗？目前只看到了识别阶段有多语种的模型提供。

[dengLG]

另外想要识别某个文本图像是属于哪个语种，可以有什么方法？

[joey-bing-614]

看你的需求来选择不同模型，通过测试选择识别率高的或者速度快的就行

…

---- Replied Message ---- | From | ***@***.***> | | Date | 08/22/2025 14:48 | | To | PaddlePaddle/PaddleOCR ***@***.***> | | Cc | joey-bing-614 ***@***.***>, Comment ***@***.***> | | Subject | Re: [PaddlePaddle/PaddleOCR] PaddleOCR/latest/version3.x/pipeline_usage/OCR (Discussion #15771) | 另外想要识别某个文本图像是属于哪个语种，可以有什么方法？ — Reply to this email directly, view it on GitHub, or unsubscribe. You are receiving this because you commented.Message ID: ***@***.***>

[MrWangChong]

我没有修改PP-OCRv5_server_rec.yml文件，训练命令：
python3 -m paddle.distributed.launch --gpus '0,1' tools/train.py -c configs/rec/PP-OCRv5/PP-OCRv5_server_rec.yml -o Global.pretrained_model=./PP-OCRv5_server_rec_pretrained.pdparams

训练结果如下：

我取的第43轮训练的结果

从测试集看效果不错，使用训练的图片测试效果也不错。

但是使用新数据来测试效果很差，原有能识别的数据，现在也识别不了了，请问一下怎么做可以避免这种情况呢？需要调PP-OCRv5_server_rec.yml里面的参数吗

🌰 Minimal Reproducible Example (最小可复现问题的Demo)

from paddleocr import TableRecognitionPipelineV2

pipeline = TableRecognitionPipelineV2(
text_recognition_model_name="PP-OCRv5_server_rec",
text_recognition_model_dir="../../PP-OCRv5_server_rec_infer/"
)
import datetime
print("识别1开始时间"+str(datetime.datetime.now()))
output = pipeline.predict("./IMG_20250901_101548.jpg")
print("识别1完成时间"+str(datetime.datetime.now()))
for res in output:
res.print() ## 打印预测的结构化输出
res.save_to_img("tabocr1")
res.save_to_json("tabocr1")

[Leolibin]

请问多语言调用服务如何指定lang具体某种语言呢？
我在请求的json中添加没有生效
payload = {"file": file_data, "fileType": 1, lang:en}
response = requests.post(API_URL, json=payload)