Updated app.py

app.py

@@ -1,11 +1,25 @@
 import gradio as gr
 from transformers import pipeline
+import numpy as np
 
-# model = "openai/whisper-small"
-# pipe = pipeline("automatic-speech-recognition", model=model)
+transcriber = pipeline("automatic-speech-recognition", model="openai/whisper-small")
 
-def greet(name):
-    return "Hello " + name + "!!"
+def transcribe(audio):
+    sr, y = audio
+    
+    # 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))
+
+    return transcriber({"sampling_rate": sr, "raw": y})["text"]  
+
+demo = gr.Interface(
+    transcribe,
+    gr.Audio(sources="microphone"),
+    "text",
+)
 
-demo = gr.Interface(fn=greet, inputs="text", outputs="text")
 demo.launch()