Update app.py

app.py

@@ -4,18 +4,23 @@ import numpy as np
 
 transcriber = pipeline("automatic-speech-recognition", model="openai/whisper-base.en")
 
-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"]
 
 
 demo = gr.Interface(
     transcribe,
-    gr.Audio(sources=["microphone"]),
-    "text",
+    ["state", gr.Audio(sources=["microphone"], streaming=True)],
+    ["state", "text"],
+    live=True,
 )
 
-demo.launch()
+demo.launch()