Update app.py

app.py

@@ -14,12 +14,17 @@ p = pipeline("automatic-speech-recognition", model=model)
 
 transcriber = pipeline("automatic-speech-recognition", model=model)
 
-def transcribe(audio):
-    sr, y = audio
+
+def transcribe(stream, new_chunk):
+    sr, y = new_chunk
     y = y.astype(np.float32)
     y /= np.max(np.abs(y))
 
-    return transcriber({"sampling_rate": sr, "raw": y})["text"]
+    if stream is not None:
+        stream = np.concatenate([stream, y])
+    else:
+        stream = y
+    return stream, transcriber({"sampling_rate": sr, "raw": stream})["text"]
 
 
 
@@ -45,8 +50,9 @@ with gr.Blocks() as demo:
     with gr.Tab("Real Time Speech Recognition"):
         with gr.Row():
             transcribe,
-            gr.Audio(sources=["microphone"]),
-            "text",
+        ["state", gr.Audio(sources=["microphone"], streaming=True)],
+        ["state", "text"],
+        live=True
 
 
 demo.launch()