Update app.py

app.py

@@ -1,66 +1,66 @@
+# Install necessary libraries if not already installed
+# !pip install transformers diffusers torch torchvision accelerate huggingface_hub matplotlib Pillow
 
-import gradio as gr 
-from transformers import MarianMTModel, MarianTokenizer, BlipProcessor, BlipForConditionalGeneration
+from huggingface_hub import login
+from transformers import MarianTokenizer, MarianMTModel
 from PIL import Image
 import torch
+from torchvision import transforms
+from transformers import BlipProcessor, BlipForConditionalGeneration
+import matplotlib.pyplot as plt
 
-# 1. Load Tamil to English translation model
-translation_model_name = "Helsinki-NLP/opus-mt-ta-en"
-tokenizer = MarianTokenizer.from_pretrained(translation_model_name)
-translation_model = MarianMTModel.from_pretrained(translation_model_name)
+# Step 1: Login to Hugging Face
+login("your_huggingface_token_here")  # 🔐 Replace this with your actual token
 
-# 2. Load BLIP model for image captioning
-caption_processor = BlipProcessor.from_pretrained("Salesforce/blip-image-captioning-base")
-caption_model = BlipForConditionalGeneration.from_pretrained("Salesforce/blip-image-captioning-base")
+# Step 2: Tamil to English Translation
+def translate_tamil_to_english(text):
+    model_name = "Helsinki-NLP/opus-mt-ta-en"
+    tokenizer = MarianTokenizer.from_pretrained(model_name)
+    model = MarianMTModel.from_pretrained(model_name)
 
-# 3. Translation function
-def translate_tamil_to_english(tamil_text):
-    if not tamil_text.strip():
-        return "No input given"
-    inputs = tokenizer(tamil_text, return_tensors="pt", padding=True, truncation=True)
-    translated = translation_model.generate(**inputs)
+    inputs = tokenizer(text, return_tensors="pt", padding=True)
+    translated = model.generate(**inputs)
     english_text = tokenizer.decode(translated[0], skip_special_tokens=True)
     return english_text
 
-# 4. Generate dummy image from text
-def generate_image_from_text(text_prompt):
-    # Use a plain color image with PIL
-    img = Image.new('RGB', (512, 512), color=(200, 230, 255))
+# Step 3: Generate Image (using any placeholder image here since BLIP is captioning-only)
+# You can download a sample image or use a real generation model like Stable Diffusion
+def get_sample_image():
+    img_url = "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/coco_sample.png"
+    img = Image.open(requests.get(img_url, stream=True).raw).convert('RGB')
     return img
 
-# 5. Describe the image
+# Step 4: Describe the Image
 def describe_image(image):
-    inputs = caption_processor(images=image, return_tensors="pt")
-    out = caption_model.generate(**inputs)
-    caption = caption_processor.decode(out[0], skip_special_tokens=True)
-    return caption
-
-# 6. Combined pipeline
-def full_pipeline(tamil_text):
-    english_text = translate_tamil_to_english(tamil_text)
-    generated_image = generate_image_from_text(english_text)
-    caption = describe_image(generated_image)
-    return english_text, generated_image, caption
+    processor = BlipProcessor.from_pretrained("Salesforce/blip-image-captioning-base")
+    model = BlipForConditionalGeneration.from_pretrained("Salesforce/blip-image-captioning-base")
 
-# 7. Gradio UI
-with gr.Blocks() as demo:
-    gr.Markdown("## 🌍 Tamil ➝ English ➝ Image ➝ Description App")
+    inputs = processor(images=image, return_tensors="pt")
+    out = model.generate(**inputs)
+    caption = processor.decode(out[0], skip_special_tokens=True)
+    return caption
 
-    with gr.Row():
-        tamil_input = gr.Textbox(label="Enter Tamil Text", lines=2, placeholder="உதாரணம்: ஒரு பூங்காவில் ஒரு பசுமை மரம் உள்ளது")
+# === MAIN ===
+if __name__ == "__main__":
+    import requests
 
-    translate_btn = gr.Button("Translate, Generate Image, and Describe")
+    # Step A: Input Tamil text
+    tamil_text = "ஒரு சிறிய வீடு கடற்கரைக்கு அருகிலுள்ளது"
+    print("Tamil Input:", tamil_text)
 
-    with gr.Row():
-        english_output = gr.Textbox(label="Translated English")
-        caption_output = gr.Textbox(label="Image Description")
+    # Step B: Translate to English
+    english_translation = translate_tamil_to_english(tamil_text)
+    print("Translated English:", english_translation)
 
-    image_output = gr.Image(label="Generated Image")
+    # Step C: Get sample image (placeholder for now, since we aren't using text-to-image yet)
+    image = get_sample_image()
 
-    translate_btn.click(
-        fn=full_pipeline,
-        inputs=tamil_input,
-        outputs=[english_output, image_output, caption_output]
-    )
+    # Step D: Describe the image
+    caption = describe_image(image)
+    print("Image Caption:", caption)
 
-demo.launch()
+    # Optional: Display the image
+    plt.imshow(image)
+    plt.title(caption)
+    plt.axis("off")
+    plt.show()