Update app.py

app.py

@@ -1,35 +1,70 @@
 import gradio as gr
 from gtts import gTTS
-import os
 import time
+import difflib
+import tempfile
+import os
+import speech_recognition as sr
 
-def read_hindi_text(text):
-    if not text.strip():
-        return "❌ Please enter some text!"
-
-    # Generate TTS
+# Function to play the text (optional)
+def play_text(text):
     tts = gTTS(text=text, lang='hi', slow=False)
-    filename = "hindi_output.mp3"
-    tts.save(filename)
+    temp_file = tempfile.NamedTemporaryFile(delete=False, suffix='.mp3')
+    tts.save(temp_file.name)
+    os.system(f"start {temp_file.name}")  # Windows
+    return "✅ Text is being read out. Please listen and read it yourself."
 
-    # Play audio
+# Function to transcribe user's audio
+def transcribe_audio(audio, original_text):
+    recognizer = sr.Recognizer()
+    with sr.AudioFile(audio) as source:
+        audio_data = recognizer.record(source)
     try:
-        os.system("start " + filename)   # Windows
-        # os.system("afplay " + filename)  # Mac
-        # os.system("xdg-open " + filename) # Linux
-        output_message = f"✅ Hindi Text saved as '{filename}' and playing now!"
+        start_time = time.time()
+        # Using Google Speech Recognition (supports Hindi)
+        transcription = recognizer.recognize_google(audio_data, language="hi-IN")
+        end_time = time.time()
+        
+        # Calculate Accuracy
+        original_words = original_text.strip().split()
+        transcribed_words = transcription.strip().split()
+        matcher = difflib.SequenceMatcher(None, original_words, transcribed_words)
+        accuracy = round(matcher.ratio() * 100, 2)
+        
+        # Calculate speed
+        duration = end_time - start_time  # time to process (not speaking time)
+        # Better: estimate speaking time from audio length if needed (advanced)
+        
+        speed = round(len(transcribed_words) / duration, 2)  # words per second
+        
+        result = {
+            "📝 Transcribed Text": transcription,
+            "🎯 Accuracy (%)": accuracy,
+            "⏱️ Speaking Speed (words/sec)": speed
+        }
+        return result
     except Exception as e:
-        output_message = f"⚠️ Error playing the file: {str(e)}"
+        return {"error": str(e)}
+
+# Gradio App
+with gr.Blocks() as app:
+    gr.Markdown("## 🗣️ Hindi Reading & Pronunciation Practice App")
     
-    return output_message
-
-# Gradio interface
-iface = gr.Interface(
-    fn=read_hindi_text,
-    inputs=gr.Textbox(lines=4, placeholder="यहाँ हिंदी टेक्स्ट लिखें..."),
-    outputs="text",
-    title="Hindi Text-to-Speech",
-    description="हिंदी टेक्स्ट डालें और 'Read' बटन दबाएँ। टेक्स्ट को आवाज़ में बदला जाएगा।"
-)
-
-iface.launch()
+    with gr.Row():
+        input_text = gr.Textbox(label="Paste Hindi Text Here", placeholder="यहाँ हिंदी टेक्स्ट लिखें...")
+        play_button = gr.Button("🔊 Listen to Text")
+
+    play_button.click(play_text, inputs=[input_text], outputs=[])
+
+    gr.Markdown("### 🎤 Now record yourself reading the text aloud below:")
+    audio_input = gr.Audio(source="microphone", type="filepath", label="Record Your Voice")
+    
+    submit_button = gr.Button("✅ Submit Recording for Checking")
+
+    output = gr.JSON(label="Results")
+
+    submit_button.click(transcribe_audio, inputs=[audio_input, input_text], outputs=[output])
+
+# Launch the app
+app.launch()
+