Update app.py

app.py

@@ -9,45 +9,12 @@ import open_clip
 
 #CONSTANTS
 
-# Carga el modelo de clasificación de imagen a texto
-blip_processor_large = AutoProcessor.from_pretrained("Salesforce/blip-image-captioning-large")
-blip_model_large = BlipForConditionalGeneration.from_pretrained("Salesforce/blip-image-captioning-large")
-
-device = "cuda" if torch.cuda.is_available() else "cpu"
-blip_model_large.to(device)
-
-
-##### IMAGE MODEL TO TEXT, MODEL 1
-def generate_caption(processor, model, image, tokenizer=None, use_float_16=False):
-    inputs = processor(images=image, return_tensors="pt").to(device)
-
-    if use_float_16:
-        inputs = inputs.to(torch.float16)
-    
-    generated_ids = model.generate(pixel_values=inputs.pixel_values, max_length=50)
-
-    if tokenizer is not None:
-        generated_caption = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
-    else:
-        generated_caption = processor.batch_decode(generated_ids, skip_special_tokens=True)[0]
-   
-    return generated_caption
-
-
-def generate_caption_coca(model, transform, image):
-    im = transform(image).unsqueeze(0).to(device)
-    with torch.no_grad(), torch.cuda.amp.autocast():
-        generated = model.generate(im, seq_len=20)
-    return open_clip.decode(generated[0].detach()).split("<end_of_text>")[0].replace("<start_of_text>", "")
-
-
 def generate_captions_speech(image):
 
     caption_blip_large = generate_caption(blip_processor_large, blip_model_large, image)
     print('generate_captions>>>'+caption_blip_large)
     return caption_blip_large,text_to_speech(caption_blip_large,"Surprise Me!")
     
-#####END IMAGE MODEL TO TEXT
     
 # Define la interfaz de usuario utilizando Gradio entradas y salidas
 inputsImg = [