Spaces:
Sleeping
Sleeping
Cryptic
commited on
Commit
·
59ff216
1
Parent(s):
98d2785
Add application file
Browse files
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"])
|