Update app.py

app.py

@@ -17,11 +17,10 @@ tokenizer = RobertaTokenizer.from_pretrained(model_name, map_location=torch.devi
 
 # function to break text into an array of sentences
 def text_to_sentences(text):
-    re.sub(r'(?<=[.!?])(?=[^\s])', r' ', text)
-    return re.split(r'[.!?]', text)
+    return re.split(r'(?<=[^A-Z].[.?]) +(?=[A-Z])', text)
 
-# function to concatenate sentences into chunks of size 600 or less
-def chunks_of_600(text, chunk_size=600):
+# function to concatenate sentences into chunks of size 900 or less
+def chunks_of_900(text, chunk_size=900):
     sentences = text_to_sentences(text)
     chunks = []
     current_chunk = ""
@@ -50,7 +49,7 @@ def predict(query, device="cpu"):
     return real
 
 def findRealProb(text):
-    chunksOfText = (chunks_of_600(text))
+    chunksOfText = (chunks_of_900(text))
     results = []
     for chunk in chunksOfText:
         output = predict(chunk)