Update app.py

app.py

@@ -17,7 +17,6 @@ nltk.download('stopwords')
 from PIL import Image
 from PIL import ImageDraw
 from PIL import ImageFont
-import time
 
 
 if not os.path.exists('./transcripts'):
@@ -151,10 +150,9 @@ def clean_text(link,start,end):
     return texts
   
   sf = pd.DataFrame(columns=['Segmented_Text','video_id'])
+
   text = segment(transcript.at[0,'text'])
-  
   for i in range(len(text)):
-    #st.write('iteration no: ',i)
     sf.loc[i, 'Segmented_Text'] = text[i]
     sf.loc[i, 'video_id'] = transcript.at[0,'video_id']
 
@@ -166,7 +164,6 @@ def clean_text(link,start,end):
     return texts
   
   for i in range(len(sf)):
-    st.write(sf.at[i, 'Segmented_Text'])
     sf.loc[i, 'Segmented_Text'] = word_seg(sf.at[i, 'Segmented_Text'])
     sf.loc[i, 'Lengths'] = len(tokenizer(sf.at[i, 'Segmented_Text'])['input_ids'])
 
@@ -203,11 +200,8 @@ def clean_text(link,start,end):
 def t5_summarizer(link,start, end):
     input_text = clean_text(link,start,end)
     lst_outputs = []
-    tokenizer1 = AutoTokenizer.from_pretrained("CareerNinja/t5_large_3e-4_on_v2_dataset")
-    st.write('Loading the model!')
-    start_time = time.time()
-    model1 = AutoModelForSeq2SeqLM.from_pretrained("CareerNinja/t5_large_3e-4_on_v2_dataset")
-    st.write('Model loading compelete, time taken: ',time.time()-start_time)
+    tokenizer1 = AutoTokenizer.from_pretrained("CareerNinja/t5-large_3e-4")
+    model1 = AutoModelForSeq2SeqLM.from_pretrained("CareerNinja/t5-large_3e-4")
     summarizer1 = pipeline("summarization", model=model1, tokenizer=tokenizer1)
     print(f""" Entered summarizer ! """)
     st.write('Below is the summary of the given URL: ')