added audio and submit button

app.py

@@ -1,27 +1,48 @@
-import gradio as gr
-import random
 import time
+import random
+import gradio as gr
+from transformers import pipeline
+
+p = pipeline("automatic-speech-recognition")
+
+def user(user_message, history):
+    return "", history + [[user_message, None]]
+
+def transcribe(audio, state=""):
+    text = p(audio)["text"]
+    state += text + " "
+    return state, state
+
+def bot(history):
+    bot_message = random.choice(["How are you?", "I love you", "I'm very hungry"])
+    history[-1][1] = ""
+    for character in bot_message:
+        history[-1][1] += character
+        time.sleep(0.05)
+        yield history
 
 with gr.Blocks() as demo:
     chatbot = gr.Chatbot()
     msg = gr.Textbox()
-    clear = gr.Button("Clear")
-
-    def user(user_message, history):
-        return "", history + [[user_message, None]]
-
-    def bot(history):
-        bot_message = random.choice(["How are you?", "I love you", "I'm very hungry"])
-        history[-1][1] = ""
-        for character in bot_message:
-            history[-1][1] += character
-            time.sleep(0.05)
-            yield history
+    gr.Interface(
+        fn=transcribe, 
+        inputs=[
+            gr.Audio(source="microphone", type="filepath", streaming=True), 
+            "state"
+        ],
+        outputs=[
+            msg,
+            "state"
+        ],
+        live=True)
+    submit = gr.Button("Submit")
 
     msg.submit(user, [msg, chatbot], [msg, chatbot], queue=False).then(
         bot, chatbot, chatbot
     )
-    clear.click(lambda: None, None, chatbot, queue=False)
+    submit.click(user, [msg, chatbot], [msg, chatbot], queue=False).then(
+        bot, chatbot, chatbot
+    )
 
 demo.queue()
-demo.launch()
+demo.launch()