have the working mic code

app.py

@@ -5,3 +5,32 @@ def greet(name):
 
 demo = gr.Interface(fn=greet, inputs="text", outputs="text")
 demo.launch()
+
+# 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))
+
+#     if stream is not None:
+#         stream = np.concatenate([stream, y])
+#     else:
+#         stream = y
+    
+#     # Return the stream as state and a string representation of the array for display
+#     return stream, str(stream)
+
+# demo = gr.Interface(
+#     transcribe,
+#     ["state", gr.Audio(sources=["microphone"], streaming=True)],
+#     ["state", "text"],
+#     live=True,
+# )
+
+# demo.launch()

working.py

@@ -0,0 +1,28 @@
+# 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))
+
+#     if stream is not None:
+#         stream = np.concatenate([stream, y])
+#     else:
+#         stream = y
+    
+#     # Return the stream as state and a string representation of the array for display
+#     return stream, str(stream)
+
+# demo = gr.Interface(
+#     transcribe,
+#     ["state", gr.Audio(sources=["microphone"], streaming=True)],
+#     ["state", "text"],
+#     live=True,
+# )
+
+# demo.launch()