Update app.py

app.py

@@ -1,5 +1,8 @@
 import gradio as gr
 from gtts import gTTS
+import speech_recognition as sr
+from difflib import SequenceMatcher
+import tempfile
 import os
 
 # Define your sentences here
@@ -16,29 +19,66 @@ sents = [
 ]
 
 def text_to_speech(selected_sentence, language):
-    # Adjust the language code for the British English accent
     tld = 'co.uk' if language == "British English" else 'com'
-    
+
     sn = int(selected_sentence.split(".")[0])  # Extract the sentence number
     mytext = sents[sn - 1]  # Get the selected sentence
 
-    # Create a gTTS object with the selected language and tld for accent
     tts = gTTS(text=mytext, lang='en', tld=tld, slow=False)
-
-    # Save the speech to a temporary file
     filename = 'output.mp3'
     tts.save(filename)
     return filename
 
-iface = gr.Interface(
-    fn=text_to_speech,
-    inputs=[
-        gr.Dropdown(choices=[f"{i}. {sents[i-1]}" for i in range(1, len(sents) + 1)], label="Select Sentence"),
-        gr.Radio(choices=['English', 'British English'], label="Language")
-    ],
-    outputs=gr.Audio(type="filepath", label="Output Audio"),
-    title="Text-to-Speech Converter",
-    description="Select a sentence and language to convert it to speech."
-)
-
-iface.launch()
+def recognize_speech_from_microphone(audio_path):
+    recognizer = sr.Recognizer()
+    try:
+        with sr.AudioFile(audio_path) as source:
+            audio_data = recognizer.record(source)
+            text = recognizer.recognize_google(audio_data)
+            return text
+    except sr.UnknownValueError:
+        return "Could not understand the audio"
+    except sr.RequestError as e:
+        return f"Could not request results from Google Speech Recognition service; {e}"
+    except Exception as e:
+        return str(e)
+
+def calculate_similarity(original_text, recognized_text):
+    return SequenceMatcher(None, original_text.lower(), recognized_text.lower()).ratio() * 100
+
+def process_audio(selected_sentence, audio_path):
+    sn = int(selected_sentence.split(".")[0])  # Extract the sentence number
+    original_text = sents[sn - 1]  # Get the selected sentence
+    recognized_text = recognize_speech_from_microphone(audio_path)
+    if "Error" in recognized_text or "Could not" in recognized_text:
+        return recognized_text, 0.0
+    similarity = calculate_similarity(original_text, recognized_text)
+    return recognized_text, similarity
+
+def display_sentence(selected_sentence):
+    sn = int(selected_sentence.split(".")[0])
+    return sents[sn - 1]
+
+with gr.Blocks() as demo:
+    with gr.Row():
+        with gr.Column():
+            gr.Markdown("### Text-to-Speech Converter")
+            dropdown_sentences = gr.Dropdown(choices=[f"{i}. {sents[i-1]}" for i in range(1, len(sents) + 1)], label="Select Sentence")
+            radio_language = gr.Radio(choices=['English', 'British English'], label="Language")
+            generate_tts_button = gr.Button("Generate Speech")
+            tts_audio_output = gr.Audio(type="filepath", label="Output Audio")
+            generate_tts_button.click(text_to_speech, inputs=[dropdown_sentences, radio_language], outputs=tts_audio_output)
+            selected_sentence_display = gr.Textbox(label="Selected Sentence", interactive=False)
+            dropdown_sentences.change(display_sentence, inputs=dropdown_sentences, outputs=selected_sentence_display)
+
+    with gr.Row():
+        with gr.Column():
+            gr.Markdown("### Pronunciation Evaluator")
+            mic_input = gr.Audio(label="Your Pronunciation", type="filepath")
+            result_button = gr.Button("Evaluate Pronunciation")
+            recognized_text = gr.Textbox(label="Recognized Text")
+            similarity_score = gr.Number(label="Similarity (%)")
+
+            result_button.click(process_audio, inputs=[dropdown_sentences, mic_input], outputs=[recognized_text, similarity_score])
+
+demo.launch()