Update app.py

app.py

@@ -1,33 +1,28 @@
 import gradio as gr
-from transformers import TrOCRProcessor, VisionEncoderDecoderModel
+from transformers import  VisionEncoderDecoderModel, AutoImageProcessor, BertTokenizerFast
 import requests
 from PIL import Image
 
-processor = TrOCRProcessor.from_pretrained("microsoft/trocr-base-handwritten")
-model = VisionEncoderDecoderModel.from_pretrained("microsoft/trocr-base-handwritten")
+image_processor = AutoImageProcessor.from_pretrained("microsoft/swin-base-patch4-window7-224")
+tokenizer = tokenizer =BertTokenizerFast.from_pretrained("onlplab/alephbert-base")
+model = VisionEncoderDecoderModel.from_pretrained("sivan22/hdd-words-ocr")
 
-# load image examples
-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
+    pixel_values = image_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]
+    generated_text = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)
 
     return generated_text
 
-title = "Interactive demo: 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 a (single-text line) image or use one of the example images below and click 'submit'. Results will show up in a few seconds."
-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>"
+title = "הדגמה: פענוח כתב יד באמצעות בינה מלאכותית"
+description = "על בסיס מודל swin בצד התמונה, ומודל alephbert בצד הטקסט."
+article = "<p style='text-align: center'>sivan22</p>"
 examples =[["image_0.png"], ["image_1.png"], ["image_2.png"]]
 
 #css = """.output_image, .input_image {height: 600px !important}"""