Update app.py

app.py

@@ -1,27 +1,41 @@
+import gradio as gr
 import azure.cognitiveservices.speech as speechsdk
 
 # Azure credentials
 speech_key = "12afe22c558a4f8d8bd28d6a67cdb9b0"
-service_region = "westus" 
+service_region = "westus"
 
-def test_speech_sdk():
+def recognize_speech(input_source, audio_file):
     try:
         speech_config = speechsdk.SpeechConfig(subscription=speech_key, region=service_region)
-        audio_config = speechsdk.audio.AudioConfig(use_default_microphone=True)
+        
+        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...")
+        print("Say something or wait for the audio file to be processed...")
         result = speech_recognizer.recognize_once()
         
         if result.reason == speechsdk.ResultReason.RecognizedSpeech:
-            print(f"Recognized: {result.text}")
+            return f"Recognized: {result.text}"
         elif result.reason == speechsdk.ResultReason.NoMatch:
-            print("No speech could be recognized")
+            return "No speech could be recognized"
         elif result.reason == speechsdk.ResultReason.Canceled:
             cancellation_details = result.cancellation_details
-            print(f"Speech Recognition canceled: {cancellation_details.reason}")
-            print(f"Error details: {cancellation_details.error_details}")
+            return f"Speech Recognition canceled: {cancellation_details.reason}\nError details: {cancellation_details.error_details}"
     except Exception as e:
-        print(f"An error occurred: {e}")
+        return f"An error occurred: {e}"
+
+iface = gr.Interface(
+    fn=recognize_speech,
+    inputs=[
+        gr.inputs.Radio(choices=["Microphone", "Audio File"], label="Input Source", default="Microphone"),
+        gr.inputs.File(label="Upload Audio File", type="file")
+    ],
+    outputs="text"
+)
 
-test_speech_sdk()
+iface.launch()