improve progressbar

app.py

@@ -38,14 +38,15 @@ else:
 
 
 def _get_increment_size(num_sents) -> int:
-    if BATCH_SIZE >= num_sents:
+    if num_sents == 1:
         return 100
     else:
-        return ceil(100 / (num_sents / BATCH_SIZE))
+        return ceil(100 / num_sents)
 
 
 btn_col, results_col = st.columns(2)
 btn_ct = btn_col.empty()
+pbar_ct = st.empty()
 error_ct = st.empty()
 simpl_ct = st.container()
 if st.session_state["text_to_simplify"]:
@@ -56,7 +57,7 @@ if st.session_state["text_to_simplify"]:
         ]
         num_sentences = len(lines)
 
-        pbar = st.progress(0, text=f"Simplifying sentences in batches of {BATCH_SIZE}...")
+        pbar = pbar_ct.progress(0, text=f"Simplifying sentences in batches of {BATCH_SIZE}...")
         increment = _get_increment_size(num_sentences)
         percent_done = 0
 
@@ -77,10 +78,11 @@ if st.session_state["text_to_simplify"]:
                 </li>"""
                 output_ct.markdown(html + "</ol>", unsafe_allow_html=True)
 
+                percent_done += increment
+                pbar.progress(min(percent_done, 100))
+
             all_simplifications.extend(simplifications)
 
-            percent_done += increment
-            pbar.progress(min(percent_done, 100))
         pbar.empty()
 
         all_simplifications = "\n".join(all_simplifications) + "\n"

utils.py

@@ -48,7 +48,7 @@ def simplify(
     """
     for batch_texts in batchify(texts, batch_size=batch_size):
         nlg_batch_texts = ["[NLG] " + text for text in batch_texts]
-        encoded = tokenizer(nlg_batch_texts, return_tensors="pt", padding=True, truncation=True)
+        encoded = tokenizer(nlg_batch_texts, return_tensors="pt", padding=True)
         encoded = {k: v.to(model.device) for k, v in encoded.items()}
         gen_kwargs = {
             "max_new_tokens": 128,