Update app.py

app.py

@@ -1,20 +1,41 @@
 import gradio as gr
-from transformers import pipeline, T5Tokenizer, T5ForConditionalGeneration
+from transformers import pipeline, T5Tokenizer, T5ForConditionalGeneration, AutoTokenizer, AutoModelForSeq2SeqLM
 import os
+import requests
+
+# Load environment variable for Hugging Face API token
 token = os.getenv("HF_TOKEN")
+headers = {"Authorization": f"Bearer {token}"}
 
+# Load summarization model and tokenizer
 tokenizer = T5Tokenizer.from_pretrained("sumedh/t5-base-amazonreviews", clean_up_tokenization_spaces=True)
 model = T5ForConditionalGeneration.from_pretrained("sumedh/t5-base-amazonreviews")
-summarizer = pipeline("summarization", model="sumedh/t5-base-amazonreviews")
+summarizer = pipeline("summarization", model=model, tokenizer=tokenizer)
+
+# Translation API details
+API_URL = "https://api-inference.huggingface.co/models/Helsinki-NLP/opus-mt-en-es"
 
+# Summarization and Translation Function
 def texto_sum(text):
-    summary = summarizer(text, do_sample=False)
-    return summary[0]['summary_text']
+    # Summarize the input text
+    summary = summarizer(text, do_sample=False)[0]['summary_text']
+    
+    # Translate summary using the Hugging Face API
+    response = requests.post(API_URL, headers=headers, json={"inputs": summary})
+    translation = response.json()
+    
+    # Check if translation is successful
+    if 'error' in translation:
+        return f"Error in translation: {translation['error']}"
+    
+    return translation[0]['translation_text']
 
+# Gradio interface
 demo = gr.Interface(
     fn=texto_sum,
     inputs=gr.Textbox(label="Texto a introducir:", placeholder="Introduce el texto a resumir aquí..."),
     outputs="text"
 )
 
+# Launch the interface
 demo.launch()