File size: 864 Bytes
fd77815
 
 
 
 
 
29406f8
fd77815
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
from transformers import AutoTokenizer
import streamlit as st
from transformers import pipeline
from transformers import (
    TFAutoModelForSequenceClassification as AutoModelForSequenceClassification,
)

st.title("Detecting Toxic Tweets")

demo = """I'm so proud of myself for accomplishing my goals today. #motivation #success"""

text = st.text_area("Input text", demo, height=250)

model_name = "distilbert-base-uncased-finetuned-sst-2-english"

tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForSequenceClassification.from_pretrained(model_name)
clf = pipeline(
    "toxicity-analysis", model=model, tokenizer=tokenizer, return_all_scores=True
)

input = tokenizer(text, return_tensors="tf")

if st.button("Submit", type="primary"):
    results = clf(text)[0]
    classes = dict(d.values() for d in results)
    st.bar_chart(classes)