All the docs

app.py

@@ -9,7 +9,6 @@ from transformers import pipeline
 from datasets import load_dataset
 import soundfile as sf
 from IPython.display import Audio
-import numpy as np
 from datasets import load_dataset
 import sentencepiece as spm
 import os
@@ -94,7 +93,7 @@ def extract_abstract(text_per_pagy):
             if start_index != -1:
                 start_index += len("Abstract") + 1
 
-                end_markers = ["Introduction", "Summary", "Overview", "Background"]
+                end_markers = ["Introduction", "Summary", "Overview", "Background", "Contents"]
                 end_index = -1
 
                 for marker in end_markers:
@@ -131,7 +130,7 @@ def main_function(uploaded_filepath):
 
     #abstract the summary with my pipeline and model, deciding the length
     summarizer = pipeline("summarization", model="pszemraj/long-t5-tglobal-base-sci-simplify")
-    summary = summarizer(abstract_text, max_length=50, min_length=30, do_sample=False)[0]['summary_text']
+    summary = summarizer(abstract_text, max_length=65, do_sample=False)[0]['summary_text']
 
     #generating the audio from the text, with my pipeline and model
     synthesiser = pipeline("text-to-speech", model="microsoft/speecht5_tts")