Update app.py

app.py

@@ -1,8 +1,4 @@
-import gradio as gr
-import torch
 import subprocess
-import speech_recognition as sr
-from TTS.api import TTS
 
 # Run the setup.py install command
 try:
@@ -11,88 +7,28 @@ try:
 except subprocess.CalledProcessError as e:
     print(f"Installation failed with error: {e}")
 
+import gradio as gr
+import torch
+from TTS.api import TTS
+
 # Get device
 device = "cuda" if torch.cuda.is_available() else "cpu"
 
 # Init TTS
 tts = TTS("tts_models/multilingual/multi-dataset/xtts_v2").to(device)
 
-# Menu Data (You can modify this as per your actual menu)
-def load_menu():
-    menu = {
-        "Breads": [
-            {"name": "Roti", "price": 1.50, "description": "Indian flatbread"},
-            {"name": "Naan", "price": 2.00, "description": "Soft leavened flatbread"}
-        ],
-        "Curries": [
-            {"name": "Butter Chicken", "price": 7.99, "description": "Creamy and rich chicken curry"},
-            {"name": "Paneer Tikka Masala", "price": 6.99, "description": "Cottage cheese in a spiced gravy"}
-        ],
-        "Biryanis": [
-            {"name": "Chicken Biryani", "price": 8.99, "description": "Fragrant rice with spiced chicken"},
-            {"name": "Vegetable Biryani", "price": 7.50, "description": "Fragrant rice with mixed vegetables"}
-        ]
-    }
-    return menu
-
-# Function to process commands and get menu details
-def process_command(command):
-    menu = load_menu()
-    
-    if 'menu' in command.lower():
-        return "Here's our menu: \n" + "\n".join([f"{category}: {', '.join([item['name'] for item in items])}" for category, items in menu.items()])
-    
-    elif 'breads' in command.lower():
-        return "Our breads: " + ", ".join([item['name'] for item in menu["Breads"]])
-
-    elif 'curries' in command.lower():
-        return "Our curries: " + ", ".join([item['name'] for item in menu["Curries"]])
-
-    elif 'biryani' in command.lower():
-        return "Our biryanis: " + ", ".join([item['name'] for item in menu["Biryanis"]])
-
-    return "I'm sorry, I didn't understand that command."
-
-# Function to recognize speech input
-def recognize_speech_from_audio(audio_file):
-    recognizer = sr.Recognizer()
-    with sr.AudioFile(audio_file) as source:
-        audio_data = recognizer.record(source)
-    try:
-        # Using Google Web Speech API for recognition
-        text = recognizer.recognize_google(audio_data)
-        print(f"Recognized text: {text}")
-        return text
-    except sr.UnknownValueError:
-        return "Sorry, I couldn't understand the speech."
-    except sr.RequestError:
-        return "Sorry, the speech service is down."
-
-# Function to generate speech (voice cloning)
 def voice_clone(text: str, speaker_wav: str, language: str):
+    # Run TTS
     print("Speaker wav:", speaker_wav)
     tts.tts_to_file(text=text, speaker_wav=speaker_wav, language=language, file_path="output.wav")
     return "output.wav"
 
-# Gradio interface for interaction
-def interact_with_assistant(user_input, speaker_audio, language):
-    if user_input:
-        response = process_command(user_input)
-    elif speaker_audio:
-        # If audio input is provided, recognize the speech
-        recognized_text = recognize_speech_from_audio(speaker_audio)
-        response = process_command(recognized_text)
-    
-    # Generate speech output for the response
-    output_audio = voice_clone(response, speaker_wav=speaker_audio, language=language)
-    return output_audio
-
-iface = gr.Interface(fn=interact_with_assistant, 
+iface = gr.Interface(fn=voice_clone, 
                      inputs=[gr.Textbox(lines=2, placeholder="Enter the text...", label="Text"),
                              gr.Audio(type="filepath", label="Upload audio file"),
                              gr.Radio(['ru', 'en', 'zh-cn', 'ja', 'de', 'fr', 'it', 'pt', 'pl', 'tr', 'ko', 'nl', 'cs', 'ar', 'es', 'hu'], label="language"),
                             ],
                      outputs=gr.Audio(type="filepath", label="Generated audio file"), 
-                     title="Voice Assistant - Menu and Voice Cloning")
+                     title="Voice Cloning")
 
 iface.launch()