Update app.py

app.py

@@ -1,17 +1,35 @@
 import yt_dlp
-import whisper
 import os
 import streamlit as st
 import transformers
 from transformers import pipeline
-from summarizer import Summarizer
-import torch
+from transformers import AutoTokenizer
+import nltk
 
 #Download youtube video
+@st.cache_data
 def download_audio(link):
     with yt_dlp.YoutubeDL({'extract_audio': True, 'format': 'bestaudio', 'outtmpl': 'video.mp3'}) as video:
         video.download(link)
 
+#Load Whisper pipeline via HuggingFace
+@st.cache_resource
+def load_whisper(seconds):
+    return pipeline("automatic-speech-recognition",
+                    model="openai/whisper-tiny",
+                    chunk_length_s=seconds,
+                   )
+
+#Load Extractive Summarizer pipeline via HuggingFace
+@st.cache_resource
+def load_extractive():
+    return pipeline("summarization",
+               model = "NotXia/longformer-bio-ext-summ",
+               tokenizer = AutoTokenizer.from_pretrained("NotXia/longformer-bio-ext-summ"),
+               trust_remote_code = True,
+               )
+
+'''
 def get_transcription_en(mp3_file):
     model = whisper.load_model("tiny.en")
     directory = os.getcwd()
@@ -43,7 +61,17 @@ def english_qa_pipeline(questions, context):
         result = nlp(question=question, context=context)
         answers.append(result["answer"])
     return answers
+'''
 
+def main():
+    sidebar = st.sidebar()
+
+    with sidebar:
+        st.title(":blue[Turing]Videos")
+
+main()
+
+'''
 #Collect inputs and create the interface
 def main():
     header = st.container()
@@ -85,4 +113,5 @@ def main():
                     for i in range(len(answers)):
                         st.write(questions[i] + ": " + answers[i])
 
-main()
+main()
+'''