Update app.py

app.py

@@ -2,6 +2,7 @@ from tempfile import NamedTemporaryFile
 from transformers import pipeline
 import streamlit as st
 from st_audiorec import st_audiorec 
+#load and cache speech recoginition model
 @st.cache_resource
 def load_model():
     pipe=pipeline("automatic-speech-recognition","distil-whisper/distil-large-v2")
@@ -16,6 +17,7 @@ def make_text(audio):
     return extract_text
 
 st.title('speech recognition, is it worth it!')
+st.write('Click start recording to record an audio in English, afterwards click stop, click on convert text once and wait')
 col1,col2=st.columns(2)
 with col1:
     with st.form(key='record audio'):
@@ -24,7 +26,7 @@ with col1:
         wave_audio_data=st_audiorec()
         
         #submit
-        button=st.form_submit_button(label='Convert to Text')
+        button=st.form_submit_button(label='Convert to Text,click once and wait')
         #if the submit button is pressed 
         if button:
             st.success('audio submitted, processing is slow give us some few seconds')
@@ -48,7 +50,7 @@ with col2:
         upload=st.file_uploader(label='Upload audio file')
 
         #submit
-        button=st.form_submit_button(label='Convert to Text')
+        button=st.form_submit_button(label='Convert to Tex. Click once and wait')
         #if the submit button is pressed 
         if button:
             st.success('audio submitted, processing is slow give us some few seconds')