Create app.py

app.py

@@ -0,0 +1,61 @@
+import gradio as gr
+import speech_recognition as sr
+import pyttsx3
+from transformers import pipeline
+
+# Initialize the text-to-speech engine
+engine = pyttsx3.init()
+
+# Initialize the transformer pipeline for NLP (Text Classification or any specific task)
+nlp = pipeline("zero-shot-classification")
+
+# Function to convert speech to text
+def speech_to_text(audio_file):
+    recognizer = sr.Recognizer()
+    with sr.AudioFile(audio_file.name) as source:
+        audio = recognizer.record(source)
+    try:
+        text = recognizer.recognize_google(audio)
+        return text
+    except sr.UnknownValueError:
+        return "Sorry, I didn't catch that."
+    except sr.RequestError:
+        return "Sorry, there's an issue with the speech recognition service."
+
+# Function to process text (handle menu ordering)
+def process_order(text):
+    # You can add your logic here for handling various food orders and preferences
+    result = nlp(text, candidate_labels=["Vegan", "Halal", "Guilt-Free", "Regular"])
+    category = result['labels'][0]
+    
+    if "Vegan" in category:
+        response = "You've chosen a Vegan dish."
+    elif "Halal" in category:
+        response = "You've chosen a Halal dish."
+    elif "Guilt-Free" in category:
+        response = "You've chosen a Guilt-Free dish."
+    else:
+        response = "You've chosen a regular dish."
+    
+    return response
+
+# Function for Text-to-Speech (Response back to user)
+def speak_response(text):
+    engine.say(text)
+    engine.runAndWait()
+
+# Create Gradio interface
+def voice_assistant(audio_file):
+    text = speech_to_text(audio_file)
+    response = process_order(text)
+    speak_response(response)
+    return response
+
+iface = gr.Interface(fn=voice_assistant, 
+                     inputs=gr.inputs.Audio(source="microphone", type="file"),
+                     outputs="text", 
+                     live=True)
+
+# Launch Gradio app
+if __name__ == "__main__":
+    iface.launch()