Create app.py

app.py

@@ -0,0 +1,15 @@
+import gradio as gr
+from transformers import pipeline
+import numpy as np
+
+def recognize_speech(audio):
+    print (type(audio))
+    transcriber = pipeline("automatic-speech-recognition", model="openai/whisper-base.en")
+    sr, y = audio
+    y = y.astype(np.float32)
+    y /= np.max(np.abs(y))
+    return transcriber({"sampling_rate": sr, "raw": y})["text"]
+
+gr.close_all()
+demo = gr.Interface(fn=recognize_speech, inputs="audio", outputs="text")
+demo.launch()