copium

app.py

@@ -1,7 +1,49 @@
 import gradio as gr
+from transformers import TrOCRProcessor, VisionEncoderDecoderModel
+import requests
+from PIL import Image
 
-def greet(name):
-    return "Hello " + name + "!!"
+processor = TrOCRProcessor.from_pretrained("microsoft/trocr-small-printed")
+model = VisionEncoderDecoderModel.from_pretrained("pENrknSoysneed/8kun-captcha-ocr-meme")
 
-iface = gr.Interface(fn=greet, inputs="text", outputs="text")
-iface.launch()
+# load image examples
+urls = [
+    'https://storage.googleapis.com/trocr-captcha.appspot.com/captcha_images_v2/nfcb5.png',
+    'https://storage.googleapis.com/trocr-captcha.appspot.com/captcha_images_v2/p57fn.png',
+    'https://storage.googleapis.com/trocr-captcha.appspot.com/captcha_images_v2/w2yp7.png',
+    'https://storage.googleapis.com/trocr-captcha.appspot.com/captcha_images_v2/pme86.png',
+    'https://storage.googleapis.com/trocr-captcha.appspot.com/captcha_images_v2/w4nfx.png',
+    'https://storage.googleapis.com/trocr-captcha.appspot.com/captcha_images_v2/nf8b8.png'
+]
+for idx, url in enumerate(urls):
+  image = Image.open(requests.get(url, stream=True).raw)
+  image.save(f"image_{idx}.png")
+
+def process_image(image):
+    # prepare image
+    pixel_values = processor(image, return_tensors="pt").pixel_values
+
+    # generate (no beam search)
+    generated_ids = model.generate(pixel_values)
+
+    # decode
+    generated_text = processor.batch_decode(generated_ids, skip_special_tokens=True)[0]
+
+    return generated_text
+
+title = "Who is that? Its a racoon ??? 2022 20021 and the year is 5400bc"
+description = "What the???? a weird graygreen racconn on my board REEEEEEEEEEEEEEEEEEEEEEEE PEEEPEEE PEPEPEEE REEEE."
+# article = "<p style='text-align: center'><a href='https://arxiv.org/abs/2109.10282'>TrOCR: Transformer-based Optical Character Recognition with Pre-trained Models</a> | <a href='https://github.com/microsoft/unilm/tree/master/trocr'>Github Repo</a></p>"
+# examples =[["image_0.png"], ["image_1.png"], ["image_2.png"], ["image_3.png"], ["image_4.png"], ["image_5.png"]]
+
+#css = """.output_image, .input_image {height: 600px !important}"""
+
+iface = gr.Interface(fn=process_image, 
+                     inputs=gr.inputs.Image(type="pil"), 
+                     outputs=gr.outputs.Textbox(),
+                     title=title,
+                     description=description,
+                    #  article=article,
+                    #  examples=examples
+                     )
+iface.launch(debug=True)