Modified app and requirements.txt

app.py

@@ -1,9 +1,25 @@
+from transformers import pipeline
 import gradio as gr
+import time
 
+p = pipeline("automatic-speech-recognition")
 
-def greet(name):
-    return "Hello " + name + "!!"
 
+def transcribe(audio, state=""):
+    time.sleep(2)
+    text = p(audio)["text"]
+    state += text + " "
+    return state, state
 
-iface = gr.Interface(fn=greet, inputs="text", outputs="text")
-iface.launch()
+
+gr.Interface(
+    fn=transcribe,
+    inputs=[
+        gr.Audio(source="microphone", type="filepath", streaming=True),
+        "state"
+    ],
+    outputs=[
+        "textbox",
+        "state"
+    ],
+    live=True).launch()

requirements.txt

@@ -1 +1,4 @@
 gradio==3.16.2
+transformers
+torch
+deepspeech==0.8.2