Update app.py

app.py

@@ -1,7 +1,6 @@
 import gradio as gr
 from transformers import pipeline, AutoTokenizer
 from sentence_transformers import SentenceTransformer, util
-import math
 
 # Translation models
 translation_models = {
@@ -45,10 +44,13 @@ def split_text(text, max_tokens=1024):
     total_tokens = len(input_ids)
     
     chunks = []
-    for i in range(0, total_tokens, max_tokens):
-        chunk_ids = input_ids[i:i+max_tokens]
+    start = 0
+    while start < total_tokens:
+        end = min(start + max_tokens, total_tokens)
+        chunk_ids = input_ids[start:end]
         chunk_text = tokenizer.decode(chunk_ids, skip_special_tokens=True)
         chunks.append(chunk_text)
+        start = end
     
     return chunks
 
@@ -92,3 +94,4 @@ iface.launch()
 
 
 
+