Update app.py

New T5 use case to summarize a paragraph of text.

app.py

@@ -230,26 +230,52 @@
 # which provides the model with some form of input and then teaches it to generate some form of target text. This makes it possible to apply 
 # the same model, loss function, hyperparameters, and other settings to all of our varied sets of responsibilities.
 
-from transformers import AutoModelWithLMHead, AutoTokenizer
-import gradio as grad
+# from transformers import AutoModelWithLMHead, AutoTokenizer
+# import gradio as grad
 
-text2text_tkn = AutoTokenizer.from_pretrained("mrm8488/t5-base-finetuned-question-generation-ap")
-mdl = AutoModelWithLMHead.from_pretrained("mrm8488/t5-base-finetuned-question-generation-ap")
+# text2text_tkn = AutoTokenizer.from_pretrained("mrm8488/t5-base-finetuned-question-generation-ap")
+# mdl = AutoModelWithLMHead.from_pretrained("mrm8488/t5-base-finetuned-question-generation-ap")
 
-def text2text(context,answer):
-    input_text = "answer: %s  context: %s </s>" % (answer, context)
-    features = text2text_tkn ([input_text], return_tensors='pt')
-    output = mdl.generate(input_ids=features['input_ids'],
-                          attention_mask=features['attention_mask'],
-                          max_length=64)
-    response=text2text_tkn.decode(output[0])
-    return response
+# def text2text(context,answer):
+#     input_text = "answer: %s  context: %s </s>" % (answer, context)
+#     features = text2text_tkn ([input_text], return_tensors='pt')
+#     output = mdl.generate(input_ids=features['input_ids'],
+#                           attention_mask=features['attention_mask'],
+#                           max_length=64)
+#     response=text2text_tkn.decode(output[0])
+#     return response
+
+# context=grad.Textbox(lines=10, label="English", placeholder="Context")
+# ans=grad.Textbox(lines=1, label="Answer")
+# out=grad.Textbox(lines=1, label="Genereated Question")
+
+# grad.Interface(text2text, inputs=[context,ans], outputs=out).launch()
 
-context=grad.Textbox(lines=10, label="English", placeholder="Context")
-ans=grad.Textbox(lines=1, label="Answer")
-out=grad.Textbox(lines=1, label="Genereated Question")
+#-----------------------------------------------------------------------------------
+# 11. Text-to-Text Generation using the T5 model - second use case summarizes a paragraph of text.
+
+from transformers import AutoTokenizer, AutoModelWithLMHead
+import gradio as grad
+
+text2text_tkn = AutoTokenizer.from_pretrained("deep-learning-analytics/wikihow-t5-small")
+mdl = AutoModelWithLMHead.from_pretrained("deep-learning-analytics/wikihow-t5-small")
+
+def text2text_summary(para):
+    initial_txt = para.strip().replace("\n","")
+    tkn_text = text2text_tkn.encode(initial_txt, return_tensors="pt")
+    tkn_ids = mdl.generate(
+        tkn_text,
+        max_length=250,
+        num_beams=5,
+        repetition_penalty=2.5,
+        early_stopping=True
+    )
+    response = text2text_tkn.decode(tkn_ids[0], skip_special_tokens=True)
+    return response
 
-grad.Interface(text2text, inputs=[context,ans], outputs=out).launch()
+para=grad.Textbox(lines=10, label="Paragraph", placeholder="Copy paragraph")
+out=grad.Textbox(lines=1, label="Summary")
 
+grad.Interface(text2text_summary, inputs=para, outputs=out).launch()