layout

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..."):
+        with st.spinner("Generating Sequence... This might take a while, thank you for your patience!"):
             sequence = generate_sequence(transformed_image, lang_id, num_beams, temperature, top_p, do_sample, top_k, max_length)
     # print(sequence)
 
@@ -136,11 +136,12 @@ def app(state):
         new_col2.write(
             "**English Translation**: "+ sequence[0] if lang_id=="en" else translate(sequence[0])
         )
-
-        try:
-            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.audio(audio_bytes)
-        except:
-            st.info("Unabled to generate audio. Please try again in some time.")
+        with new_col2:
+            try:
+                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.audio(audio_bytes)
+            except:
+                st.info("Unabled to generate audio. Please try again in some time.")

sections/usage.md

@@ -4,4 +4,6 @@
 
 - The sidebar contains generation parameters such as `Number of Beams`, `Top-P`, `Temperature` which will be used when generating the caption.
 
-- Lastly, one can choose the `Language` of the caption in the dropdown below to generate a caption in that particular language.
+- One can choose the `Language` of the caption in the dropdown below to generate a caption in that particular language.
+
+- Lastly, keeping in mind its intended future scope for visually challenged people, we also provide audio clip for the generated sequence.