Download tokenizer

app.py

@@ -20,6 +20,8 @@ df = pd.read_csv(filename)
 df.drop_duplicates(inplace=True)
 print(f'Number of documents: {len(df)}')
 
+nltk.download('punkt')
+
 corpus = []
 sentence_count = []
 for _, row in df.iterrows():
@@ -107,4 +109,4 @@ iface = gr.Interface(
     ],
     allow_flagging=False
 )
-iface.launch()
+iface.launch()