Update app.py

app.py

@@ -1,64 +1,48 @@
-import gradio as gr
-from huggingface_hub import InferenceClient
+# Install necessary libraries first
+!pip install gradio transformers sentencepiece
 
-"""
-For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
-"""
-client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
+# Now, import everything
+import gradio as gr
+from transformers import MarianMTModel, MarianTokenizer
 
+# Load models
+en_to_ur_model_name = "Helsinki-NLP/opus-mt-en-ur"
+ur_to_en_model_name = "Helsinki-NLP/opus-mt-ur-en"
 
-def respond(
-    message,
-    history: list[tuple[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-):
-    messages = [{"role": "system", "content": system_message}]
+en_to_ur_tokenizer = MarianTokenizer.from_pretrained(en_to_ur_model_name)
+en_to_ur_model = MarianMTModel.from_pretrained(en_to_ur_model_name)
 
-    for val in history:
-        if val[0]:
-            messages.append({"role": "user", "content": val[0]})
-        if val[1]:
-            messages.append({"role": "assistant", "content": val[1]})
+ur_to_en_tokenizer = MarianTokenizer.from_pretrained(ur_to_en_model_name)
+ur_to_en_model = MarianMTModel.from_pretrained(ur_to_en_model_name)
 
-    messages.append({"role": "user", "content": message})
+# Define translation functions
+def translate_en_to_ur(text):
+    inputs = en_to_ur_tokenizer(text, return_tensors="pt", padding=True)
+    translated = en_to_ur_model.generate(**inputs)
+    result = en_to_ur_tokenizer.decode(translated[0], skip_special_tokens=True)
+    return result
 
-    response = ""
+def translate_ur_to_en(text):
+    inputs = ur_to_en_tokenizer(text, return_tensors="pt", padding=True)
+    translated = ur_to_en_model.generate(**inputs)
+    result = ur_to_en_tokenizer.decode(translated[0], skip_special_tokens=True)
+    return result
 
-    for message in client.chat_completion(
-        messages,
-        max_tokens=max_tokens,
-        stream=True,
-        temperature=temperature,
-        top_p=top_p,
-    ):
-        token = message.choices[0].delta.content
+# Create Gradio Interface
+with gr.Blocks() as app:
+    gr.Markdown("## 📝 English ↔ Urdu Translator (Free, Open Source)")
 
-        response += token
-        yield response
+    with gr.Row():
+        input_text = gr.Textbox(lines=4, placeholder="Enter your text here...")
 
+    with gr.Row():
+        en_to_ur_button = gr.Button("Translate English → Urdu")
+        ur_to_en_button = gr.Button("Translate Urdu → English")
 
-"""
-For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
-"""
-demo = gr.ChatInterface(
-    respond,
-    additional_inputs=[
-        gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
-        gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
-        gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
-        gr.Slider(
-            minimum=0.1,
-            maximum=1.0,
-            value=0.95,
-            step=0.05,
-            label="Top-p (nucleus sampling)",
-        ),
-    ],
-)
+    output_text = gr.Textbox(lines=4, label="Translated Text")
 
+    en_to_ur_button.click(fn=translate_en_to_ur, inputs=input_text, outputs=output_text)
+    ur_to_en_button.click(fn=translate_ur_to_en, inputs=input_text, outputs=output_text)
 
-if __name__ == "__main__":
-    demo.launch()
+# Launch app
+app.launch()