UI

apps/mic.py

@@ -124,7 +124,7 @@ def app(state):
 
     sequence = ['']
     if new_col2.button("Generate Caption", help="Generate a caption in the specified language."):
-        with st.spinner("Generating Sequence... This might take a while, thank you for your patience!"):
+        with st.spinner("Generating Sequence... This might take some time, you can read our Article meanwhile!"):
             sequence = generate_sequence(transformed_image, lang_id, num_beams, temperature, top_p, do_sample, top_k, max_length)
     # print(sequence)
 
@@ -141,7 +141,7 @@ def app(state):
                 clean_text = re.sub(r'[^A-Za-z0-9 ]+', '', sequence[0])
                 # st.write("**Cleaned Text**: ",clean_text)
                 audio_bytes = voicerss_tts(clean_text, lang_id)
-                st.write("audio for the generated caption")
+                st.markdown("**Audio for the generated caption**")
                 st.audio(audio_bytes)
             except:
                 st.info("Unabled to generate audio. Please try again in some time.")