Upload audio

app.py

@@ -4,13 +4,14 @@ import numpy as np
 
 transcriber = pipeline("automatic-speech-recognition", model="openai/whisper-base.en")
 
+
 def transcribe(stream, new_chunk):
     sr, y = new_chunk
-    
+
     # Convert to mono if stereo
     if y.ndim > 1:
         y = y.mean(axis=1)
-        
+
     y = y.astype(np.float32)
     y /= np.max(np.abs(y))
 
@@ -18,14 +19,14 @@ def transcribe(stream, new_chunk):
         stream = np.concatenate([stream, y])
     else:
         stream = y
-    return stream, transcriber({"sampling_rate": sr, "raw": stream})["text"]  
+    return stream, transcriber({"sampling_rate": sr, "raw": stream})["text"]
+
 
 demo = gr.Interface(
     transcribe,
-    ["state", gr.Audio(sources=["microphone"], streaming=True)],
+    ["state", gr.Audio(sources=["upload"], streaming=True)],
     ["state", "text"],
     live=True,
 )
 
 demo.launch()
-