Update app.py

app.py

@@ -9,16 +9,18 @@ tokenizer = BertTokenizer.from_pretrained('ProsusAI/finbert')
 
 model = BertForSequenceClassification.from_pretrained('ProsusAI/finbert')
 
-#summarizer = pipeline('summarization', model='t5-base')
+summarizer = pipeline('summarization', model='t5-base')
 
+classifier_emotions = ['positive', 'neutral', 'negative']
 # classifier_model_name = 'bhadresh-savani/distilbert-base-uncased-emotion'
 # classifier_emotions = ['anger', 'disgust', 'fear', 'joy', 'sadness', 'surprise']
 
-def get_sentiment(tokens):
-    outputs = model(**tokens)
-    probabilities = torch.nn.functional.softmax(outputs[0], dim=-1 )
-    return probabilities
-
+def summarize_sentences(sentences_by_emotion, min_length, max_length):
+    for k in sentences_by_emotion.keys():
+        if (len(sentences_by_emotion[k])!=0):
+            text = ' '.join(sentences_by_emotion[k])
+            summary = summarizer(text, min_length=min_length, max_length=max_length)
+            print(f"{k.upper()}: {summary[0]['summary_text']}\n")
 
 
 def chunk_text_to_window_size_and_predict_proba(input_ids, attention_mask, total_len):
@@ -36,7 +38,7 @@ def chunk_text_to_window_size_and_predict_proba(input_ids, attention_mask, total
         proba_list (List[torch.Tensor]): List of probability tensors for each chunk.
     """
     proba_list = []
-    
+
     start = 0
     window_length = 510
     
@@ -64,6 +66,9 @@ def chunk_text_to_window_size_and_predict_proba(input_ids, attention_mask, total
         }
         
         outputs = model(**input_dict)
+
+        decoded = tokenizer.decode(input_ids_chunk)
+        print("########:", decoded , ":##############")
         
         probabilities = torch.nn.functional.softmax(outputs[0], dim = -1)
         proba_list.append(probabilities)
@@ -115,6 +120,7 @@ def my_inference_function(sec_text):
     """
     tokens = tokenizer.encode_plus(sec_text, add_special_tokens=False)
     
+    
     input_ids = tokens['input_ids']
     total_len = len(input_ids)
     attention_mask = tokens['attention_mask']