Update app.py

app.py

@@ -1,9 +1,9 @@
 import time
 import random
 import gradio as gr
-# from transformers import pipeline
+from transformers import pipeline
 
-# p = pipeline("automatic-speech-recognition")
+p = pipeline("automatic-speech-recognition", "facebook/wav2vec2-base-960h")
 
 def user(user_message, history):
     return "", history + [[user_message, None]]
@@ -76,17 +76,16 @@ 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=0.85):
+            with gr.Column(scale=0.70):
                 txt = gr.Textbox(
                     show_label=False,
                     placeholder="Type your response and press enter, or record your response",
                 ).style(container=False)
             with gr.Column(scale=0.15, 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")
+                record = gr.Audio(source="microphone", type="filepath", show_label=False)
+            with gr.Column(scale=0.15, min_width=0):
+                speech = gr.Button("Submit")
+
         # gr.Interface(
         #     fn=transcribe, 
         #     inputs=[
@@ -99,11 +98,13 @@ with gr.Blocks(css=css) as demo:
         #     ],
         #     live=True)
                 
-        submit = gr.Button("Submit")
+        send = gr.Button("Send")
+
+        speech.click(transcribe, inputs=record, outputs=txt)
         txt.submit(user, [txt, chatbot], [txt, chatbot], queue=False).then(
             bot, chatbot, chatbot
         )
-        submit.click(user, [txt, chatbot], [txt, chatbot], queue=False).then(
+        send.click(user, [txt, chatbot], [txt, chatbot], queue=False).then(
             bot, chatbot, chatbot
         )