Fix Convert2Markdown

app.py → src/app.py

@@ -16,7 +16,7 @@ FILENAME = ""
 preprocess = TextExtractor()
 model_name = "sshleifer/distill-pegasus-cnn-16-4"
 device = "cuda" if torch.cuda.is_available() else "cpu"
-tokenizer = PegasusTokenizer.from_pretrained(model_name, max_length=500)
+tokenizer = PegasusTokenizer.from_pretrained(model_name)
 model = PegasusForConditionalGeneration.from_pretrained(model_name).to(device)
 
 def summarize(slides):
@@ -34,11 +34,10 @@ def summarize(slides):
                     print("Summarization Fails")
     return generated_slides
 
-
-def convert2markdown(generate_slides):
-    mdFile = MdUtils(file_name=FILENAME, title=f'{FILENAME} Presentation')
-    for k, v in generate_slides.items():
-        mdFile.new_paragraph('---')
+def convert2markdown(generated_slides):
+    mdFile = MdUtils(file_name=f"summary/{FILENAME}", title=f'{FILENAME} Presentation')
+    for k, v in generated_slides.items():
+        mdFile.new_line('---\n')
         for section in v:
             tag = section[0]
             content = section[1]
@@ -47,7 +46,7 @@ def convert2markdown(generate_slides):
             if tag == 'p':
                 contents = content.split('<n>')
                 for content in contents:
-                    mdFile.new_paragraph(content)
+                    mdFile.new_line(f"{content}\n")
     mdFile.create_md_file()
     return f"{FILENAME}.md"