Update app.py

app.py

@@ -1,60 +1,33 @@
-from flask import Flask, render_template, request, jsonify
-import speech_recognition as sr
-import pyttsx3
-import sounddevice as sd
-import numpy as np
+from flask import Flask, request, jsonify
+from transformers import pipeline
+import os
 
 app = Flask(__name__)
 
-def speak(text):
-    engine = pyttsx3.init()
-    engine.say(text)
-    engine.runAndWait()
+# Load ASR model
+asr_pipeline = pipeline("automatic-speech-recognition", model="facebook/wav2vec2-large-960h")
 
-def get_voice_input(prompt, timeout=30):
-    recognizer = sr.Recognizer()
-    microphone = sr.Microphone()
-    
-    speak(prompt)
-    
-    with microphone as source:
-        print(prompt)
-        recognizer.adjust_for_ambient_noise(source)
-        try:
-            audio = recognizer.listen(source, timeout=timeout)
-        except sr.WaitTimeoutError:
-            speak("Time is up. Please try again.")
-            return None
-    
-    try:
-        text = recognizer.recognize_google(audio)
-        print(f"Recognized: {text}")
-        return text
-    except sr.UnknownValueError:
-        speak("Sorry, I could not understand. Please repeat.")
-        return None
-    except sr.RequestError:
-        speak("Speech service is unavailable right now.")
-        return None
+# Store user data
+user_data = {"name": "", "email": ""}
 
-@app.route('/')
-def home():
-    return render_template('index.html')
-
-@app.route('/voice_input', methods=['POST'])
+@app.route("/voice_input", methods=["POST"])
 def voice_input():
-    data = request.json
-    field = data.get("field")
-    if field == "username":
-        prompt = "Please tell me your name"
-    elif field == "email":
-        prompt = "Please tell me your email address"
-    else:
-        return jsonify({"error": "Invalid field"}), 400
+    file = request.files["audio"]
+    file_path = "temp.wav"
+    file.save(file_path)
+
+    # Convert Speech to Text
+    text = asr_pipeline(file_path)["text"]
+
+    # Check which field is missing
+    if user_data["name"] == "":
+        user_data["name"] = text
+        return jsonify({"message": "Name recorded", "name": text})
+    elif user_data["email"] == "":
+        user_data["email"] = text
+        return jsonify({"message": "Email recorded", "email": text})
     
-    response = get_voice_input(prompt, timeout=30)
-    return jsonify({"response": response})
+    return jsonify({"message": "All details recorded", "data": user_data})
 
 if __name__ == "__main__":
-    speak("Welcome to Biryani Hub")
     app.run(debug=True)