Create app.py

app.py

@@ -0,0 +1,57 @@
+import requests
+from PIL import Image
+
+url = "https://fki.tic.heia-fr.ch/static/img/a01-122-02.jpg"
+image = Image.open(requests.get(url, stream=True).raw).convert("RGB")
+
+from transformers import TrOCRProcessor
+
+processor = TrOCRProcessor.from_pretrained("microsoft/trocr-base-handwritten")
+# calling the processor is equivalent to calling the feature extractor
+pixel_values = processor(image, return_tensors="pt").pixel_values
+print(pixel_values.shape)
+
+from transformers import VisionEncoderDecoderModel
+
+model = VisionEncoderDecoderModel.from_pretrained("microsoft/trocr-base-handwritten")
+generated_ids = model.generate(pixel_values)
+generated_text = processor.batch_decode(generated_ids, skip_special_tokens=True)[0]
+#print(generated_text)
+
+import gradio as gr
+from transformers import TrOCRProcessor, VisionEncoderDecoderModel
+import requests
+from PIL import Image
+
+processor = TrOCRProcessor.from_pretrained("microsoft/trocr-base-handwritten")
+model = VisionEncoderDecoderModel.from_pretrained("microsoft/trocr-base-handwritten")
+# load image examples from the IAM database
+urls = ['https://fki.tic.heia-fr.ch/static/img/a01-122-02.jpg', 'https://encrypted-tbn0.gstatic.com/images?q=tbn:ANd9GcSoolxi9yWGAT5SLZShv8vVd0bz47UWRzQC19fDTeE8GmGv_Rn-PCF1pP1rrUx8kOjA4gg&usqp=CAU',
+        'https://encrypted-tbn0.gstatic.com/images?q=tbn:ANd9GcRNYtTuSBpZPV_nkBYPMFwVVD9asZOPgHww4epu9EqWgDmXW--sE2o8og40ZfDGo87j5w&usqp=CAU']
+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 = "Handwritten text Recognition Using TrOCR"
+description = "Demo for Microsoft's TrOCR, an encoder-decoder model consisting of an image Transformer encoder and a text Transformer decoder for state-of-the-art optical character recognition (OCR) on single-text line images. This particular model is fine-tuned on IAM, a dataset of annotated handwritten images. To use it, simply upload an image or use the example image below and click 'submit'. Results will show up in a few seconds."
+#article = "TrOCR: Transformer-based Optical Character Recognition with Pre-trained Models | Github Repo"
+examples =[["image_0.png"], ["image_1.png"], ["image_2.png"]]
+
+iface = gr.Interface(fn=process_image, 
+                     inputs=gr.inputs.Image(type="pil"), 
+                     outputs=gr.outputs.Textbox(),
+                     title=title,
+                     description=description,
+                     examples=examples)
+iface.launch(inline=False)