Update functions.py

functions.py

@@ -65,12 +65,29 @@ def inference(link, upload):
       results = asr_model.transcribe(upload)
       
       return results, "Transcribed Earnings Audio"
+
+@st.experimental_memo(suppress_st_warning=True)       
+def chunk_long_text(text,threshold):
+    '''Chunk long text'''
+    sentences = sent_tokenize(text)
+    out = []
+
+    for chunk in sentences:
+        if len(chunk.split()) < threshold:
+            out.append(chunk)
+        else:
+            words = chunk.split()
+            num = int(len(words)/threshold)
+            for i in range(0,num*threshold+1,threshold):
+                out.append(' '.join(words[i:threshold+i]))
+
+    return out
       
 @st.experimental_memo(suppress_st_warning=True)
 def sentiment_pipe(earnings_text):
     '''Determine the sentiment of the text'''
     
-    earnings_sentences = sent_tokenize(earnings_text)
+    earnings_sentences = chunk_long_text(earnings_text,400)
     earnings_sentiment = sent_pipe(earnings_sentences)
     
     return earnings_sentiment, earnings_sentences