Spaces:
Running
Running
wavesoumen
commited on
Commit
•
a73cc46
1
Parent(s):
92f170e
start
Browse files
app.py
ADDED
@@ -0,0 +1,42 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
import streamlit as st
|
2 |
+
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
|
3 |
+
import nltk
|
4 |
+
|
5 |
+
# Download NLTK data
|
6 |
+
nltk.download('punkt')
|
7 |
+
|
8 |
+
# Load the tokenizer and model
|
9 |
+
tokenizer = AutoTokenizer.from_pretrained("fabiochiu/t5-base-tag-generation")
|
10 |
+
model = AutoModelForSeq2SeqLM.from_pretrained("fabiochiu/t5-base-tag-generation")
|
11 |
+
|
12 |
+
# Streamlit app title
|
13 |
+
st.title("Text to Tags Generation")
|
14 |
+
|
15 |
+
# Text area for user input
|
16 |
+
text = st.text_area("Enter the text for tag extraction:", height=200)
|
17 |
+
|
18 |
+
# Button to generate tags
|
19 |
+
if st.button("Generate Tags"):
|
20 |
+
if text:
|
21 |
+
try:
|
22 |
+
# Tokenize and encode the input text
|
23 |
+
inputs = tokenizer([text], max_length=512, truncation=True, return_tensors="pt")
|
24 |
+
|
25 |
+
# Generate tags
|
26 |
+
output = model.generate(**inputs, num_beams=8, do_sample=True, min_length=10, max_length=64)
|
27 |
+
|
28 |
+
# Decode the output
|
29 |
+
decoded_output = tokenizer.batch_decode(output, skip_special_tokens=True)[0]
|
30 |
+
|
31 |
+
# Extract unique tags
|
32 |
+
tags = list(set(decoded_output.strip().split(", ")))
|
33 |
+
|
34 |
+
# Display the tags
|
35 |
+
st.write("**Generated Tags:**")
|
36 |
+
st.write(tags)
|
37 |
+
except Exception as e:
|
38 |
+
st.error(f"An error occurred: {e}")
|
39 |
+
else:
|
40 |
+
st.warning("Please enter some text to generate tags.")
|
41 |
+
|
42 |
+
# To run this app, save this code to a file (e.g., `app.py`) and run `streamlit run app.py` in your terminal.
|