Update app.py

app.py

@@ -13,6 +13,10 @@ def user(user_message, history):
 #     state += text + " "
 #     return state, state
 
+def transcribe(audio):
+    text = p(audio)["text"]
+    return text
+
 def bot(history):
     bot_message = random.choice(["How are you?", "I love you", "I'm very hungry"])
     history[-1][1] = ""
@@ -72,15 +76,17 @@ with gr.Blocks(css=css) as demo:
     
         # with gr.Row():
         with gr.Row(elem_id="prompt-container").style(mobile_collapse=False, equal_height=True):
-            with gr.Column(scale=0.80):
+            with gr.Column(scale=0.85):
                 txt = gr.Textbox(
                     show_label=False,
                     placeholder="Type your response and press enter, or record your response",
                 ).style(container=False)
-            with gr.Column(scale=0.10, min_width=0):
-                record = gr.Audio(source="microphone", type="filepath", streaming=True)
-            with gr.Column(scale=0.10, min_width=0):
-                submit = gr.Button("Submit")
+            with gr.Column(scale=0.15, min_width=0):
+                # record = gr.Audio(source="microphone", type="filepath", show_label=False)
+                gr.Interface(
+                    fn=transcribe, 
+                    inputs=gr.Audio(source="microphone", type="filepath", show_label=False), 
+                    outputs="text")
         # gr.Interface(
         #     fn=transcribe, 
         #     inputs=[
@@ -92,7 +98,8 @@ with gr.Blocks(css=css) as demo:
         #         "state"
         #     ],
         #     live=True)
-
+                
+        submit = gr.Button("Submit")
         txt.submit(user, [txt, chatbot], [txt, chatbot], queue=False).then(
             bot, chatbot, chatbot
         )