Update app.py

app.py

@@ -35,7 +35,7 @@ import torch
 #import torchaudio
 #import torchaudio.transforms as transforms
 
-from transformers import pipeline, AutoTokenizer, AutoModelForSeq2SeqLM
+from transformers import pipeline, AutoModel
 
 import spacy
 import networkx as nx
@@ -101,6 +101,11 @@ def transcribe_audio(audio_file, batch_size=16):
     return text.strip(), system_info
 
 #              ------------summary section------------
+
+
+
+#          -----------------BLOCKS NEED EDIT....!--------------
+
 @spaces.GPU()
 def clean_text(text):
     text = re.sub(r'https?:\/\/.*[\r\n]*', '', text)
@@ -112,6 +117,9 @@ nlp = spacy.blank("nb")  # 'nb' ==> codename = Norwegian Bokmål
 nlp.add_pipe('sentencizer')
 spacy_stop_words = spacy.lang.nb.stop_words.STOP_WORDS
 
+summarization_model = AutoModel.from_pretrained("NbAiLab/nb-bert-large")
+# pipe = pipeline("fill-mask", model="NbAiLab/nb-bert-large")
+
 @spaces.GPU()
 def preprocess_text(text):
     # Process the text with SpaCy
@@ -122,7 +130,6 @@ def preprocess_text(text):
     words = [token.text for token in doc if token.text.lower() not in stop_words]
     return ' '.join(words)
 
-# Summarize w/T5 model
 @spaces.GPU()
 def summarize_text(text):
     preprocessed_text = preprocess_text(text)
@@ -130,7 +137,8 @@ def summarize_text(text):
     inputs = inputs.to(device)
     summary_ids = summarization_model.generate(inputs.input_ids, num_beams=5, max_length=150, early_stopping=True)
     return summarization_tokenizer.decode(summary_ids[0], skip_special_tokens=True)
-
+    
+@spaces.GPU()
 def build_similarity_matrix(sentences, stop_words):
     similarity_matrix = nx.Graph()
     for i, tokens_a in enumerate(sentences):
@@ -141,6 +149,7 @@ def build_similarity_matrix(sentences, stop_words):
     return similarity_matrix
 
 # PageRank
+@spaces.GPU()
 def graph_based_summary(text, num_paragraphs=3):
     doc = nlp(text)
     sentences = [sent.text for sent in doc.sents]
@@ -157,8 +166,8 @@ def graph_based_summary(text, num_paragraphs=3):
     return ' '.join([sent for _, sent in ranked_sentences[:num_paragraphs]])
 
 # LexRank
+@spaces.GPU()
 def lex_rank_summary(text, num_paragraphs=3, threshold=0.1):
-
     doc = nlp(text)
     sentences = [sent.text for sent in doc.sents]
     if len(sentences) < num_paragraphs:
@@ -177,8 +186,8 @@ def lex_rank_summary(text, num_paragraphs=3, threshold=0.1):
     return ' '.join([ranked_sentences[i][1] for i in range(num_paragraphs)])
 
 # TextRank
+@spaces.GPU()
 def text_rank_summary(text, num_paragraphs=3):
-
     doc = nlp(text)
     sentences = [sent.text for sent in doc.sents]
     if len(sentences) < num_paragraphs:
@@ -268,7 +277,7 @@ with iface:
            
             """)
         
-      @      summarize_transcribed_button_text_rank = gr.Button("Summary of Transcribed Text, Click Here")
+            summarize_transcribed_button_text_rank = gr.Button("Summary of Transcribed Text, Click Here")
             summarize_transcribed_button_text_rank.click(fn=lambda text: text_rank_summary(text), inputs=[text_output], outputs=[summary_output_text_rank])
             summarize_uploaded_button_text_rank = gr.Button("Upload Text to Summarize, Click Here")
             summarize_uploaded_button_text_rank.click(fn=text_rank_summary, inputs=[text_input_text_rank], outputs=[summary_output_text_rank])