Update app.py

app.py

@@ -5,8 +5,6 @@ from gtts import gTTS
 import os
 import sqlite3
 from sklearn.ensemble import IsolationForest
-import sounddevice as sd
-import numpy as np
 import speech_recognition as sr
 
 # Initialize Database
@@ -16,23 +14,6 @@ cursor.execute('''CREATE TABLE IF NOT EXISTS preferences (id INTEGER PRIMARY KEY
 cursor.execute('''CREATE TABLE IF NOT EXISTS history (id INTEGER PRIMARY KEY, command TEXT, response TEXT)''')
 conn.commit()
 
-def record_audio():
-    samplerate = 16000
-    duration = 5  # seconds
-    recording = sd.rec(int(samplerate * duration), samplerate=samplerate, channels=1, dtype='float64')
-    sd.wait()  # Wait until recording is finished
-    return np.squeeze(recording)
-
-def recognize_audio():
-    r = sr.Recognizer()
-    audio = record_audio()
-    with sr.AudioData(audio.tobytes(), 16000, 2) as source:
-        try:
-            command = r.recognize_google(source)
-            return command
-        except sr.UnknownValueError:
-            return "Sorry, I could not understand the audio."
-            
 # Anomaly Detection Model
 anomaly_model = IsolationForest(contamination=0.1)
 data = []
@@ -81,16 +62,42 @@ def detect_anomalies(command):
             return True
     return False
 
-# Gradio Interface
-def assistant(command):
+# Gradio Interface for Audio and Text Input
+def assistant(input_audio=None, input_text=""):
+    if input_audio:
+        # Process audio input
+        recognizer = sr.Recognizer()
+        with sr.AudioFile(input_audio) as source:
+            audio = recognizer.record(source)
+            try:
+                command = recognizer.recognize_google(audio)
+            except sr.UnknownValueError:
+                return "Sorry, I could not understand the audio.", ""
+    else:
+        # Process text input
+        command = input_text
+
+    # Check anomalies
     if detect_anomalies(command):
         return "Warning: Anomalous behavior detected!", ""
+
+    # Process command
     response = process_command(command)
     log_history(command, response)
+
+    # Text-to-Speech Output
     tts = gTTS(text=response, lang='en')
     tts.save("response.mp3")
     return response, "response.mp3"
 
-# Launch App
-demo = gr.Interface(fn=assistant, inputs="text", outputs=["text", "audio"])
+# Gradio Interface with Audio and Text Input Options
+demo = gr.Interface(
+    fn=assistant,
+    inputs=[
+        gr.Audio(source="microphone", type="filepath", optional=True),  # Audio input
+        gr.Textbox(label="Text Command", placeholder="Type a command...")  # Text input
+    ],
+    outputs=["text", "audio"]
+)
+
 demo.launch()