Initial commit3

app.py

@@ -18,11 +18,16 @@ if torch.cuda.is_available():
     model = model.cuda()
 
 # OCR function
-def ocr_from_image(image, ocr_type):
-    if image is None:
+def ocr_from_image(image_file, ocr_type):
+    if image_file is None:
         return "Please upload an image."
+
+    # Ouvrir le fichier image avec PIL
+    image = Image.open(image_file).convert("RGB")
     image_path = "uploaded_image.jpg"
     image.save(image_path)
+
+    # Passer le chemin au modele
     res = model.chat(tokenizer, image_path, ocr_type=ocr_type)
     return res
 
@@ -37,9 +42,9 @@ iface = gr.Interface(
         gr.Radio(ocr_types, label="OCR Type", value="ocr")
     ],
     outputs="text",
-    title="🧠 GOT-OCR2.0 Transformer OCR",
+    title="?? GOT-OCR2.0 Transformer OCR",
     description="Upload an image file and select the OCR type: plain text (`ocr`) or formatted (`format`)."
 )
 
 if __name__ == "__main__":
-    iface.launch()
+    iface.launch(share=True)

app.py.bak

@@ -1,50 +1,45 @@
-import os
 import gradio as gr
-from transformers import TrOCRProcessor, TrOCRForConditionalGeneration
+from transformers import AutoModel, AutoTokenizer
 from PIL import Image
 import torch
 
-# ?? Chargement du modele et du processor
-model_name = "microsoft/trocr-base-handwritten"
-model = TrOCRForConditionalGeneration.from_pretrained(model_name)
-processor = TrOCRProcessor.from_pretrained(model_name)
-
-device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
-model.to(device)
-model.eval()
-
-# ?? Fonction OCR
-def ocr_from_image(image_file, ocr_type):
-    if image_file is None:
-        return "Veuillez importer une image."
-
-    # Pretraitement de l'image
-    image = Image.open(image_file.name).convert("RGB")
-    pixel_values = processor(images=image, return_tensors="pt").pixel_values.to(device)
-
-    # Generation de texte
-    with torch.no_grad():
-        generated_ids = model.generate(pixel_values)
-
-    # Decodage du texte genere
-    generated_text = processor.tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
-    return generated_text
-
-# ?? Types d'OCR (juste pour l'interface ici)
+# Load model and tokenizer
+tokenizer = AutoTokenizer.from_pretrained('ucaslcl/GOT-OCR2_0', trust_remote_code=True)
+model = AutoModel.from_pretrained(
+    'ucaslcl/GOT-OCR2_0',
+    trust_remote_code=True,
+    low_cpu_mem_usage=True,
+    device_map='cuda' if torch.cuda.is_available() else 'cpu',
+    use_safetensors=True,
+    pad_token_id=tokenizer.eos_token_id
+)
+model = model.eval()
+if torch.cuda.is_available():
+    model = model.cuda()
+
+# OCR function
+def ocr_from_image(image, ocr_type):
+    if image is None:
+        return "Please upload an image."
+    image_path = "uploaded_image.jpg"
+    image.save(image_path)
+    res = model.chat(tokenizer, image_path, ocr_type=ocr_type)
+    return res
+
+# OCR types to choose from
 ocr_types = ["ocr", "format"]
 
-# ?? Interface Gradio
+# Gradio interface
 iface = gr.Interface(
     fn=ocr_from_image,
     inputs=[
-        gr.File(label="Importer une image", file_types=[".jpg", ".jpeg", ".png"]),
-        gr.Radio(ocr_types, label="Type d'OCR", value="ocr")
+        gr.File(label="Upload Image", file_types=[".jpg", ".jpeg", ".png"]),
+        gr.Radio(ocr_types, label="OCR Type", value="ocr")
     ],
     outputs="text",
-    title="?? OCR manuscrit avec TrOCR",
-    description="Importez une image manuscrite pour extraire le texte avec le modele Microsoft TrOCR."
+    title="🧠 GOT-OCR2.0 Transformer OCR",
+    description="Upload an image file and select the OCR type: plain text (`ocr`) or formatted (`format`)."
 )
 
-# ?? Lancement
 if __name__ == "__main__":
     iface.launch()