Update app.py

app.py

@@ -1,4 +1,3 @@
-from transformers import M2M100ForConditionalGeneration, M2M100Tokenizer
 from transformers import MBartForConditionalGeneration, MBart50Tokenizer, pipeline
 import gradio as gr
 import requests
@@ -12,7 +11,7 @@ model_name = "facebook/mbart-large-50-many-to-one-mmt"
 tokenizer = MBart50Tokenizer.from_pretrained(model_name)
 model = MBartForConditionalGeneration.from_pretrained(model_name)
 
-# Use GPT-2 for text generation instead of LLaMA
+# Use GPT-2 for text generation instead of restricted models
 text_gen_model = "gpt2"
 pipe = pipeline(
     "text-generation", 
@@ -23,7 +22,7 @@ pipe = pipeline(
 
 # Use the Hugging Face API key from environment variables for text-to-image model
 API_URL = "https://api-inference.huggingface.co/models/ZB-Tech/Text-to-Image"
-headers = {"Authorization": f"Bearer {os.getenv('hf_token')}"}
+headers = {"Authorization": f"Bearer {os.getenv('full_token')}"}
 
 # Define the translation, text generation, and image generation function
 def translate_and_generate_image(tamil_text):
@@ -34,7 +33,7 @@ def translate_and_generate_image(tamil_text):
     translated_text = tokenizer.batch_decode(translated_tokens, skip_special_tokens=True)[0]
 
     # Step 2: Generate descriptive English text using GPT-2
-    generated_text = pipe(translated_text, max_length=100, num_return_sequences=1)[0]['generated_text']
+    generated_text = pipe(translated_text, max_length=50, num_return_sequences=1, truncation=True)[0]['generated_text']
     
     # Step 3: Use the generated English text to create an image
     def query(payload):
@@ -58,5 +57,5 @@ iface = gr.Interface(
     description="Translate Tamil text to English using Facebook's mbart-large-50 model, generate descriptive text using GPT-2, and create an image using the generated text.",
 )
 
-# Launch Gradio app with a shareable link
-iface.launch(share=True)
+# Launch Gradio app without `share=True` (Hugging Face Spaces already handles sharing)
+iface.launch()