Cryptic commited on
Commit
59ff216
·
1 Parent(s): 98d2785

Add application file

Browse files
Files changed (1) hide show
  1. app.py +33 -0
app.py ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ import streamlit as st
2
+ from transformers import pipeline
3
+
4
+ # Load models optimized for CPU
5
+ transcriber = pipeline("automatic-speech-recognition", model="openai/whisper-tiny.en", device=-1)
6
+ summarizer = pipeline("summarization", model="sshleifer/distilbart-cnn-12-6", device=-1)
7
+ question_generator = pipeline("text2text-generation", model="google/t5-efficient-tiny", device=-1)
8
+
9
+ # Streamlit UI
10
+ st.title("Curate AI - Audio Transcription and Summarization")
11
+
12
+ uploaded_file = st.file_uploader("Upload an audio file", type=["wav", "mp3", "m4a"])
13
+ if uploaded_file is not None:
14
+ st.audio(uploaded_file, format='audio/wav')
15
+
16
+ # Transcribing the audio
17
+ st.write("Transcribing the audio...")
18
+ lecture_text = transcriber(uploaded_file)["text"]
19
+ st.write("Transcription: ", lecture_text)
20
+
21
+ # Summarization
22
+ st.write("Summarizing the transcription...")
23
+ num_words = len(lecture_text.split())
24
+ max_length = min(num_words, 1024) # Max input for BART is 1024 tokens
25
+ summary = summarizer(lecture_text, max_length=1024, min_length=int(max_length * 0.1), truncation=True)
26
+ st.write("Summary: ", summary[0]['summary_text'])
27
+
28
+ # Question Generation
29
+ context = f"Based on the following lecture summary: {summary[0]['summary_text']}, generate some relevant practice questions."
30
+ st.write("Generating questions...")
31
+ questions = question_generator(context, max_new_tokens=50)
32
+ for question in questions:
33
+ st.write(question["generated_text"])