Duplicate from StarCore/PaddleOCR

Co-authored-by: StarSpace <StarCore@users.noreply.huggingface.co>

.gitattributes

@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,13 @@
+---
+title: PaddleOCR
+emoji: 😻
+colorFrom: purple
+colorTo: indigo
+sdk: gradio
+sdk_version: 3.40.1
+app_file: app.py
+pinned: false
+duplicated_from: StarCore/PaddleOCR
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,34 @@
+import gradio as gr
+
+from pp_ocr import inference_img, inference_json
+
+title = "基于PP-OCRv3文本识别"
+description = """
+    PaddleOCR是百度开源的超轻量级OCR模型库，提供了数十种文本检测、识别模型，旨在打造一套丰富、领先、实用的文字检测、识别模型/工具库。
+    > 项目地址：PaddleOCR github 地址： https://github.com/PaddlePaddle/PaddleOCR
+"""
+
+with gr.Blocks() as app:
+    gr.Markdown("<h1 style='text-align: center; margin-bottom: 1rem'>"
+                + title
+                + "</h1>")
+    gr.Markdown(description)
+    with gr.Tab("图片"):
+        with gr.Row():
+            with gr.Column():
+                img_input = gr.Image()
+                img_btn = gr.Button("识别")
+            with gr.Column():
+                img_output = gr.Image(label="Result")
+    with gr.Tab("JSON"):
+        with gr.Row():
+            with gr.Column():
+                json_input = gr.Image()
+                json_btn = gr.Button("识别")
+            with gr.Column():
+                json_output = gr.Json(label="Result")
+
+    img_btn.click(inference_img, inputs=img_input, outputs=img_output)
+    json_btn.click(inference_json, inputs=json_input, outputs=json_output)
+
+app.launch()

pp_ocr.py

@@ -0,0 +1,18 @@
+import tempfile
+import os
+
+import paddlehub as hub
+from PIL import Image
+
+pp_ocrv3 = hub.Module(name="ch_pp-ocrv3")
+
+def inference_img(img):
+    with tempfile.TemporaryDirectory() as tempdir_name:
+        pp_ocrv3.recognize_text(images=[img], use_gpu=False, output_dir=tempdir_name, visualization=True)
+        result_names = os.listdir(tempdir_name)
+        result_image = Image.open(os.path.join(tempdir_name, result_names[0]))
+        return result_image
+    
+def inference_json(img):
+        results = pp_ocrv3.recognize_text(images=[img], use_gpu=False, visualization=False)
+        return results

requirements.txt

@@ -0,0 +1,3 @@
+paddlepaddle==2.4.2
+paddlehub
+gradio