Update app.py

app.py

@@ -2,15 +2,18 @@ import gradio as gr
 from gtts import gTTS
 import os
 import uuid
+import tempfile
 from transformers import pipeline
 from deep_translator import GoogleTranslator
-import tempfile
-from langdetect import detect
+import fasttext
 
-# Load Hugging Face model for intelligent responses
+# Load language detection model
+lang_model = fasttext.load_model("lid.176.bin")
+
+# Load Hugging Face model
 qa_pipeline = pipeline("text2text-generation", model="google/flan-t5-base")
 
-# 🌱 Knowledge base for plant and soil questions
+# Plant/Soil knowledge base
 knowledge_base = {
     "best soil for gardening": "Loamy soil is best for gardening because it retains moisture and nutrients but also drains well.",
     "best soil for tomato": "Tomatoes grow best in well-drained loamy soil that is rich in organic matter.",
@@ -19,54 +22,53 @@ knowledge_base = {
     "what soil for roses": "Roses grow well in loamy, well-drained soil with a pH between 6.0 and 7.0."
 }
 
+# FastText-based language detection
 def detect_language(text):
-    try:
-        return detect(text)
-    except:
-        return "en"
+    lang = lang_model.predict(text)[0][0].replace("__label__", "")
+    return lang
 
 def generate_response(text):
-    # Detect language and translate to English for processing
+    # Detect language and translate
     original_lang = detect_language(text)
     translated_input = GoogleTranslator(source='auto', target='en').translate(text)
 
-    # Use knowledge base for specific questions
+    # Use knowledge base if match
     response_text = ""
     for key in knowledge_base:
         if key in translated_input.lower():
             response_text = knowledge_base[key]
             break
 
-    # Otherwise, use the Hugging Face model
+    # Otherwise use Hugging Face model
     if not response_text:
         response_text = qa_pipeline(translated_input, max_length=100)[0]['generated_text']
 
-    # Translate response back to original language
+    # Translate back to original language
     translated_response = GoogleTranslator(source='en', target=original_lang).translate(response_text)
 
-    # Text to speech in original language
+    # Text-to-speech
     try:
         tts = gTTS(text=translated_response, lang=original_lang)
-    except ValueError:
-        tts = gTTS(text=translated_response, lang='en')  # fallback
-    audio_file = f"{uuid.uuid4()}.mp3"
-    audio_path = os.path.join(tempfile.gettempdir(), audio_file)
+    except:
+        tts = gTTS(text=translated_response, lang='en')
+
+    audio_path = os.path.join(tempfile.gettempdir(), f"{uuid.uuid4()}.mp3")
     tts.save(audio_path)
 
     return translated_response, audio_path
 
-# Gradio Interface
+# Gradio UI
 with gr.Blocks() as demo:
-    gr.Markdown("🌍 **Multilingual Voice Chatbot**\nAsk me anything in your language. I'll respond in voice & text!")
+    gr.Markdown("🌍 **Multilingual Voice Chatbot**\nAsk in any language about plants/soil!")
 
     with gr.Row():
         with gr.Column():
-            text_input = gr.Textbox(label="💬 Your Question")
-            ask_button = gr.Button("Ask")
+            text_input = gr.Textbox(label="🌱 Ask a Question")
+            ask_button = gr.Button("🧠 Get Answer")
 
         with gr.Column():
-            text_output = gr.Textbox(label="📝 Bot Response")
-            audio_output = gr.Audio(label="🎧 Bot Voice", autoplay=True)
+            text_output = gr.Textbox(label="📝 Response")
+            audio_output = gr.Audio(label="🔊 Voice", autoplay=True)
 
     ask_button.click(fn=generate_response, inputs=text_input, outputs=[text_output, audio_output])