Update app.py

app.py

@@ -10,8 +10,8 @@ transcriber = pipeline(task="automatic-speech-recognition", model="geokanaan/Whi
 HF_TOKEN = os.getenv('WRITE')
 hf_writer = gr.HuggingFaceDatasetSaver(HF_TOKEN, "flagged_Audio_Lebanese")
 
-def transcribe(stream, new_chunk):
-    sr, y = new_chunk
+def transcribe(audio):
+    sr, y = audio
     
     # Convert to mono if stereo
     if y.ndim > 1:
@@ -20,19 +20,14 @@ def transcribe(stream, new_chunk):
     y = y.astype(np.float32)
     y /= np.max(np.abs(y))
 
-    if stream is not None:
-        stream = np.concatenate([stream, y])
-    else:
-        stream = y
-    return stream, transcriber({"sampling_rate": sr, "raw": stream})["text"]  
+    return transcriber({"sampling_rate": sr, "raw": y})["text"]  
 
     
 demo = gr.Interface(
     transcribe,
-    ["state", gr.Audio(sources=["microphone"], streaming=True)],
-    ["state", "text"],
-    live=True,
-    title="UNDER MAINTENANCE",
+    gr.Audio(sources=["microphone"],
+    "text",
+    title="Arabeasy",
     description="Realtime demo for Lebanese Arabizi speech recognition",
     allow_flagging='manual',  # Enable manual flagging
 )