Update app.py

app.py

@@ -1,70 +1,45 @@
-import gradio as gr
-import speech_recognition as sr
-import torch
+from flask import Flask, render_template, request, jsonify
 import os
+import torch
+import speech_recognition as sr
 from transformers import pipeline
 from gtts import gTTS
-import time
 
-# Load ASR Model (Whisper)
+app = Flask(__name__)
+recognizer = sr.Recognizer()
+
+# Load Hugging Face Whisper Model
 device = "cuda" if torch.cuda.is_available() else "cpu"
 speech_to_text = pipeline("automatic-speech-recognition", model="openai/whisper-base", device=0 if device == "cuda" else -1)
 
-# Initialize Speech Recognition
-recognizer = sr.Recognizer()
-
-# Function to Play Audio Prompt
-def play_audio(text):
-    tts = gTTS(text=text, lang='en')
-    filename = "prompt.mp3"
+# Function to convert text to speech
+def generate_audio(text, filename="static/output.mp3"):
+    tts = gTTS(text=text, lang="en")
     tts.save(filename)
-    os.system(f"mpg321 {filename}" if os.name != "nt" else f"start {filename}")  # Works on Linux & Windows
-    time.sleep(2)  # Give some time for the speech to play
 
-# Function to Capture Name
-def capture_name(audio):
-    play_audio("Tell me your name")
+@app.route("/")
+def home():
+    return render_template("index.html")
+
+@app.route("/get_prompt")
+def get_prompt():
+    generate_audio("Welcome to Biryani Hub. Please tell me your name.", "static/welcome.mp3")
+    return jsonify({"audio_url": "/static/welcome.mp3"})
+
+@app.route("/process_audio", methods=["POST"])
+def process_audio():
+    if "audio" not in request.files:
+        return jsonify({"error": "No audio file"}), 400
+    
+    audio_file = request.files["audio"]
+    audio_path = "static/temp.wav"
+    audio_file.save(audio_path)
+    
     try:
-        text = speech_to_text(audio)["text"]
-        return f"👤 Name Captured: {text}", "Please provide your email address."
+        text = speech_to_text(audio_path)["text"]
+        return jsonify({"text": text})
     except Exception as e:
-        return f"❌ Error: {str(e)}", ""
-
-# Function to Capture Email
-def capture_email(audio):
-    play_audio("Please provide your email address")
-    try:
-        text = speech_to_text(audio)["text"]
-        return f"📧 Email Captured: {text}"
-    except Exception as e:
-        return f"❌ Error: {str(e)}"
-
-# Gradio Interface
-def gradio_interface():
-    with gr.Blocks() as demo:
-        gr.Markdown("<h1 style='text-align: center;'>🍽️ AI Dining Assistant</h1>")
-        
-        with gr.Column():
-            gr.Image("/mnt/data/image.png", elem_id="header_image", show_label=False)  # Upload the image you provided
-            gr.Markdown("<p style='text-align: center;'>Press the mic button to start...</p>")
-
-            gr.Markdown("#### 🎤 Step 1: Tell me your name")
-            mic_button = gr.Button("🎙️ Tap to Speak Your Name")
-            audio_input_name = gr.Audio(type="filepath", visible=False)
-            name_output = gr.Textbox(label="Your Name:")
-            email_prompt_output = gr.Textbox(label="Next Step:", interactive=False)
-
-            mic_button.click(capture_name, inputs=audio_input_name, outputs=[name_output, email_prompt_output])
-
-            gr.Markdown("#### 🎤 Step 2: Provide your email")
-            mic_button_email = gr.Button("🎙️ Tap to Speak Your Email")
-            audio_input_email = gr.Audio(type="filepath", visible=False)
-            email_output = gr.Textbox(label="Your Email:")
-
-            mic_button_email.click(capture_email, inputs=audio_input_email, outputs=email_output)
-
-    return demo
+        return jsonify({"error": str(e)}), 500
 
-# Launch the Gradio Interface
-demo = gradio_interface()
-demo.launch(debug=True)
+if __name__ == "__main__":
+    app.run(host="0.0.0.0", port=7860, debug=True)