Update app.py

app.py

@@ -3,7 +3,7 @@ from google.cloud import speech_v1
 from google.protobuf import timestamp_pb2
 
 
-def transcribe(audio_bytes):
+def transcribe(stream, audio_bytes):
     """Transcribe audio bytes to text using Google Cloud Speech to Text."""
 
     # Crea un cliente de Speech to Text
@@ -19,19 +19,24 @@ def transcribe(audio_bytes):
     audio = speech_v1.RecognitionAudio(content=audio_bytes)
     request = speech_v1.RecognizeSpeechRequest(config=config, audio=audio)
 
-    # Realiza la transcripción
-    response = client.recognize_speech(request)
-
-    # Extrae el texto transcrito
-    transcript = response.results[0].alternatives[0].transcript
-
-    return transcript
+    sr, y = audio_bytes
+    y = y.astype(np.float32)
+    y /= np.max(np.abs(y))
+    if stream is not None:
+        # Realiza la transcripción
+        response = client.recognize_speech(request)
+    
+        # Extrae el texto transcrito
+        transcript = response.results[0].alternatives[0].transcript
+    else:
+        stream = y
+    return stream, transcript
 
 
 demo = gr.Interface(
     transcribe,
-    gr.Audio(sources=["microphone"], streaming=True),
-    "text",
+    ["state", gr.Audio(sources=["microphone"], streaming=True)],
+    ["state", "text"],
     live=True,
 )