Create app.py

app.py

@@ -0,0 +1,24 @@
+import gradio as gr
+from transformers import pipeline
+import time
+
+pipe = pipeline("automatic-speech-recognition", model="openai/whisper-base.en")
+
+def transcribe(audio, state=""):
+    print(audio)
+    time.sleep(2)
+    text = pipe(audio)["text"]
+    state += text + " "
+    return state, state
+
+
+with gr.Blocks() as demo:
+  state = gr.State(value="")
+  with gr.Row():
+      with gr.Column():
+        audio = gr.Audio(source="microphone", type="filepath") 
+      with gr.Column():
+        textbox = gr.Textbox()
+  audio.stream(fn=transcribe, inputs=[audio, state], outputs=[textbox, state])
+
+demo.launch(debug=True)