Update app.py

app.py

@@ -6,9 +6,9 @@ from transformers import AutoModelForSeq2SeqLM, AutoTokenizer
 import torch
 
 #### Model 1 ####
-model_name = "snrspeaks/t5-one-line-summary"
-model = AutoModelForSeq2SeqLM.from_pretrained(model_name)
-tokenizer = AutoTokenizer.from_pretrained(model_name)
+#model_name = "snrspeaks/t5-one-line-summary"
+#model = AutoModelForSeq2SeqLM.from_pretrained(model_name)
+#tokenizer = AutoTokenizer.from_pretrained(model_name)
 
 #### Model 2 ####
 summarizer = pipeline(
@@ -31,15 +31,15 @@ params = {
 
 #### Run the model 1####
 def summarize(text):
-    input_ids = tokenizer.encode("summarize: " + text, return_tensors="pt", add_special_tokens=True)
-    generated_id = model.generate(input_ids=input_ids,num_beams=5,max_length=50,repetition_penalty=2.5,length_penalty=1,early_stopping=True,num_return_sequences=1)
-    pred = tokenizer.decode(generated_id[0], skip_special_tokens=True, clean_up_tokenization_spaces=True)
+    #input_ids = tokenizer.encode("summarize: " + text, return_tensors="pt", add_special_tokens=True)
+    #generated_id = model.generate(input_ids=input_ids,num_beams=5,max_length=50,repetition_penalty=2.5,length_penalty=1,early_stopping=True,num_return_sequences=1)
+    #pred = tokenizer.decode(generated_id[0], skip_special_tokens=True, clean_up_tokenization_spaces=True)
 
     result = summarizer(text, **params)
     pred2 = result[0]['summary_text']
 
-    output = pred + "\n\n" + pred2
-    return output
+    #output = pred + "\n\n" + pred2
+    return pred2
 
 #### Display summarized text ####
 with gr.Blocks() as demo: