Update app.py

app.py

@@ -1,43 +1,54 @@
 import gradio as gr
 import whisper
-import difflib  # To compare expected vs actual pronunciation
+import difflib
 
-# Load the Whisper model
+# Load the Whisper model (base model is a good balance between speed and accuracy)
 model = whisper.load_model("base")
 
 def pronunciation_feedback(transcription, reference_text):
     """
-    Function to give basic feedback on pronunciation based on differences
-    between the transcribed text and the reference text.
+    Function to provide basic pronunciation feedback by comparing the transcription
+    with the reference (expected) text.
     """
+    # Compare transcription with reference text using difflib
     diff = difflib.ndiff(reference_text.split(), transcription.split())
-    errors = [word for word in diff if word.startswith('- ')]  # Find words missing or mispronounced
+    
+    # Identify words that are incorrect or missing in transcription
+    errors = [word for word in diff if word.startswith('- ')]
+    
     if errors:
-        feedback = "You mispronounced the following words: " + ', '.join([error[2:] for error in errors])
+        feedback = "Mispronounced words: " + ', '.join([error[2:] for error in errors])
     else:
         feedback = "Great job! Your pronunciation is spot on."
+    
     return feedback
 
 def transcribe_and_feedback(audio, reference_text):
     """
-    Transcribes audio and provides pronunciation feedback.
+    Transcribe the audio and provide pronunciation feedback.
     """
-    # Transcribe the audio using Whisper
+    # Transcribe the audio using Whisper model
     result = model.transcribe(audio)
     transcription = result['text']
     
-    # Provide basic pronunciation feedback
+    # Provide pronunciation feedback
     feedback = pronunciation_feedback(transcription, reference_text)
     
     return transcription, feedback
 
-# Create the Gradio interface for real-time transcription and feedback
+# Set up the Gradio interface
 interface = gr.Interface(
-    fn=transcribe_and_feedback,  # Function to transcribe and give feedback
-    inputs=[gr.Audio(source="microphone", type="filepath"), gr.Textbox(label="Expected Text")],
-    outputs=[gr.Textbox(label="Transcription"), gr.Textbox(label="Pronunciation Feedback")],
-    live=True  # Enables real-time transcription
+    fn=transcribe_and_feedback,  # Function to transcribe and provide feedback
+    inputs=[
+        gr.Audio(source="microphone", type="filepath"),  # Live audio input
+        gr.Textbox(label="Expected Text")  # User provides the reference text
+    ],
+    outputs=[
+        gr.Textbox(label="Transcription"),  # Display transcription
+        gr.Textbox(label="Pronunciation Feedback")  # Display feedback
+    ],
+    live=True  # Enable real-time transcription
 )
 
-# Launch the Gradio interface
+# Launch the Gradio interface on Hugging Face Spaces
 interface.launch(share=True)