update the app.py to include a new model

app.py

@@ -26,15 +26,28 @@ base_model = VisionEncoderDecoderModel.from_pretrained('Edgar404/donut-shivi-rec
 base_processor = DonutProcessor.from_pretrained('Edgar404/donut-shivi-recognition')
 print('Loading complete')
 
-print('Loading the optimized model ....')
+print('Loading the latence optimized model ....')
 optimized_model = VisionEncoderDecoderModel.from_pretrained('Edgar404/donut-shivi-cheques_KD_320')
 optimized_processor = DonutProcessor.from_pretrained('Edgar404/donut-shivi-cheques_KD_320')
 print('Loading complete')
 
+print('Loading the performance optimized model ....')
+performance_model = VisionEncoderDecoderModel.from_pretrained('Edgar404/donut-shivi-cheques_1920')
+performance_processor = DonutProcessor.from_pretrained('Edgar404/donut-shivi-cheques_1920')
+print('Loading complete')
+
+models = {'baseline': base_model ,
+         'performance': performance_model ,
+         'latence': optimized_model}
+
+processor = {'baseline': base_processor ,
+         'performance': performance_processor ,
+         'latence': optimized_processor}
+
 # setting
 
 
-def process_image(image , mode = 'optimized' ):
+def process_image(image , mode = 'baseline' ):
     """ Function that takes an image and perform an OCR using the model DonUT via the task document
     parsing
 
@@ -42,9 +55,9 @@ def process_image(image , mode = 'optimized' ):
     __________
     image : a machine readable image of class PIL or numpy"""
 
-    model = optimized_model if mode == 'optimized' else base_model
-    processor = optimized_processor if mode == 'optimized' else base_processor
-    d_type = torch.bfloat16 if ((mode == 'optimized') & (device =='cuda')) else torch.float32
+    model = models[mode]
+    processor = processor[mode]
+    d_type = torch.float32 
 
     model.to(device)
     model.eval()