Update app.py

app.py

@@ -1,41 +1,33 @@
-import gradio as gr
+import streamlit as st
 import azure.cognitiveservices.speech as speechsdk
 
-# Azure credentials
+# Azure Speech Service credentials
 speech_key = "12afe22c558a4f8d8bd28d6a67cdb9b0"
 service_region = "westus"
 
-def recognize_speech(input_source, audio_file):
-    try:
-        speech_config = speechsdk.SpeechConfig(subscription=speech_key, region=service_region)
-        
-        if input_source == "Microphone":
-            audio_config = speechsdk.audio.AudioConfig(use_default_microphone=True)
-        else:
-            audio_config = speechsdk.audio.AudioConfig(filename=audio_file.name)
-        
-        speech_recognizer = speechsdk.SpeechRecognizer(speech_config=speech_config, audio_config=audio_config)
-        
-        print("Say something or wait for the audio file to be processed...")
-        result = speech_recognizer.recognize_once()
-        
-        if result.reason == speechsdk.ResultReason.RecognizedSpeech:
-            return f"Recognized: {result.text}"
-        elif result.reason == speechsdk.ResultReason.NoMatch:
-            return "No speech could be recognized"
-        elif result.reason == speechsdk.ResultReason.Canceled:
-            cancellation_details = result.cancellation_details
-            return f"Speech Recognition canceled: {cancellation_details.reason}\nError details: {cancellation_details.error_details}"
-    except Exception as e:
-        return f"An error occurred: {e}"
+def transcribe_audio(file_path):
+    speech_config = speechsdk.SpeechConfig(subscription=speech_key, region=service_region)
+    audio_input = speechsdk.AudioConfig(filename=file_path)
+    speech_recognizer = speechsdk.SpeechRecognizer(speech_config=speech_config, audio_config=audio_input)
 
-iface = gr.Interface(
-    fn=recognize_speech,
-    inputs=[
-        gr.Radio(choices=["Microphone", "Audio File"], label="Input Source", value="Microphone"),
-        gr.File(label="Upload Audio File", type="file")
-    ],
-    outputs=gr.Textbox()
-)
+    result = speech_recognizer.recognize_once()
+    if result.reason == speechsdk.ResultReason.RecognizedSpeech:
+        return result.text
+    elif result.reason == speechsdk.ResultReason.NoMatch:
+        return "No speech could be recognized"
+    else:
+        return "Speech recognition canceled: {}".format(result.cancellation_details.reason)
 
-iface.launch()
+st.title("Chinese Pronunciation Checker")
+
+uploaded_file = st.file_uploader("Choose an audio file", type=["wav", "mp3"])
+
+if uploaded_file is not None:
+    st.audio(uploaded_file, format="audio/wav")
+    file_path = f"temp_audio.{uploaded_file.type.split('/')[-1]}"
+    
+    with open(file_path, "wb") as f:
+        f.write(uploaded_file.getbuffer())
+
+    transcript = transcribe_audio(file_path)
+    st.write("Transcribed Text: ", transcript)