Update app.py

app.py

@@ -28,6 +28,7 @@ st.markdown(
     This app assists finance analysts with transcribing and analysis Earnings Calls by carrying out the following tasks:
     - Transcribing earnings calls using Open AI's [Whisper](https://github.com/openai/whisper).
     - Analysing the sentiment of transcribed text using the quantized version of [FinBert-Tone](https://huggingface.co/nickmuchi/quantized-optimum-finbert-tone).
+    - Summarization of the call with [FaceBook-Bart](https://huggingface.co/facebook/bart-large-cnn) model with entity extraction
     - Semantic search engine with [Sentence-Transformers](https://huggingface.co/sentence-transformers/all-mpnet-base-v2) and reranking results with a Cross-Encoder.
     
     **👇 Enter a YouTube Earnings Call URL below and navigate to the sidebar tabs** 
@@ -54,11 +55,13 @@ def load_models():
     asr_model = whisper.load_model("small")
     q_model = ORTModelForSequenceClassification.from_pretrained("nickmuchi/quantized-optimum-finbert-tone")
     q_tokenizer = AutoTokenizer.from_pretrained("nickmuchi/quantized-optimum-finbert-tone")
+    sent_pipe = pipeline("text-classification",model=q_model, tokenizer=q_tokenizer)
+    sum_pipe = pipeline("summarization",model="facebook/bart-large-cnn", tokenizer="facebook/bart-large-cnn")
     cross_encoder = CrossEncoder('cross-encoder/ms-marco-MiniLM-L-12-v2')
     
-    return asr_model, q_model, q_tokenizer, cross_encoder
+    return asr_model, sent_pipe, sum_pipe, cross_encoder
     
-asr_model, q_model, q_tokenizer, cross_encoder = load_models()
+asr_model, sent_pipe, sum_pipe, cross_encoder  = load_models()
 
 @st.experimental_memo(suppress_st_warning=True)
 def inference(link, upload):
@@ -83,11 +86,10 @@ def inference(link, upload):
 def sentiment_pipe(earnings_text):
     '''Determine the sentiment of the text'''
     
-    remote_clx = pipeline("text-classification",model=q_model, tokenizer=q_tokenizer)
-
-    earnings_sentiment = remote_clx(sent_tokenize(earnings_text))
+    earnings_sentences = sent_tokenize(earnings_text)
+    earnings_sentiment = sent_pipe(earnings_sentences)
     
-    return earnings_sentiment    
+    return earnings_sentiment, earnings_sentences    
     
 @st.experimental_memo(suppress_st_warning=True)
 def preprocess_plain_text(text,window_size=3):
@@ -151,4 +153,4 @@ def fin_ext(text):
     results = remote_clx(sent_tokenizer(text))
     return make_spans(text,results)
 
-progress_bar.empty()    
+progress_bar.empty()