Spaces:
Sleeping
Sleeping
Commit
•
6421cd0
1
Parent(s):
1a863cf
Update app.py
Browse files
app.py
CHANGED
@@ -1,40 +1,41 @@
|
|
1 |
-
import streamlit as st
|
2 |
-
import torch
|
3 |
-
|
4 |
-
# from datasets import DatasetDict, Dataset
|
5 |
-
|
6 |
-
# # Load train, test, and validation JSON files
|
7 |
-
# train_data = Dataset.from_json('jsonDataTrain.json')
|
8 |
-
# test_data = Dataset.from_json('jsonDataTest.json')
|
9 |
-
# validation_data = Dataset.from_json('jsonDataVal.json')
|
10 |
-
|
11 |
-
# # Define the features
|
12 |
-
# features = ['Post', 'defamation', 'hate', 'non-hostile', 'offensive']
|
13 |
-
|
14 |
-
labels = ['hate', 'non-hostile', 'defamation', 'offensive']
|
15 |
-
id2label = {idx:label for idx, label in enumerate(labels)}
|
16 |
-
label2id = {label:idx for idx, label in enumerate(labels)}
|
17 |
-
|
18 |
-
from transformers import BertTokenizer, BertForSequenceClassification
|
19 |
-
|
20 |
-
# Load the fine-tuned model and tokenizer
|
21 |
-
model_name = "fine_tuned_hindi_bert_model"
|
22 |
-
tokenizer = BertTokenizer.from_pretrained(model_name)
|
23 |
-
model = BertForSequenceClassification.from_pretrained(model_name)
|
24 |
-
|
25 |
-
# Example input text
|
26 |
-
input_text = "मैं एक छात्र हूं जो छात्रावास में रहता हूं और दृढ़ संकल्प के साथ अपनी पढ़ाई करता हूं लेकिन मेरा दोस्त मूर्ख है। वह हर समय गेम खेलता है और खाना खाता है।"
|
27 |
-
|
28 |
-
|
29 |
-
|
30 |
-
|
31 |
-
|
32 |
-
|
33 |
-
|
34 |
-
|
35 |
-
|
36 |
-
|
37 |
-
|
38 |
-
|
39 |
-
|
|
|
40 |
st.write(id2label[i], predicted_class[0][i].item())
|
|
|
1 |
+
import streamlit as st
|
2 |
+
import torch
|
3 |
+
|
4 |
+
# from datasets import DatasetDict, Dataset
|
5 |
+
|
6 |
+
# # Load train, test, and validation JSON files
|
7 |
+
# train_data = Dataset.from_json('jsonDataTrain.json')
|
8 |
+
# test_data = Dataset.from_json('jsonDataTest.json')
|
9 |
+
# validation_data = Dataset.from_json('jsonDataVal.json')
|
10 |
+
|
11 |
+
# # Define the features
|
12 |
+
# features = ['Post', 'defamation', 'hate', 'non-hostile', 'offensive']
|
13 |
+
|
14 |
+
labels = ['hate', 'non-hostile', 'defamation', 'offensive']
|
15 |
+
id2label = {idx:label for idx, label in enumerate(labels)}
|
16 |
+
label2id = {label:idx for idx, label in enumerate(labels)}
|
17 |
+
|
18 |
+
from transformers import BertTokenizer, BertForSequenceClassification
|
19 |
+
|
20 |
+
# Load the fine-tuned model and tokenizer
|
21 |
+
model_name = "fine_tuned_hindi_bert_model"
|
22 |
+
tokenizer = BertTokenizer.from_pretrained(model_name)
|
23 |
+
model = BertForSequenceClassification.from_pretrained(model_name)
|
24 |
+
|
25 |
+
# Example input text
|
26 |
+
# input_text = "मैं एक छात्र हूं जो छात्रावास में रहता हूं और दृढ़ संकल्प के साथ अपनी पढ़ाई करता हूं लेकिन मेरा दोस्त मूर्ख है। वह हर समय गेम खेलता है और खाना खाता है।"
|
27 |
+
st.title("Hate Speech Classificsation Demo")
|
28 |
+
|
29 |
+
input_text = st.input_text(input)
|
30 |
+
|
31 |
+
# Tokenize the input text
|
32 |
+
inputs = tokenizer(input_text, return_tensors="pt")
|
33 |
+
|
34 |
+
# Perform inference
|
35 |
+
with torch.no_grad():
|
36 |
+
outputs = model(**inputs)
|
37 |
+
|
38 |
+
# Get the predicted class
|
39 |
+
predicted_class = outputs.logits
|
40 |
+
for i in range(len(predicted_class[0])):
|
41 |
st.write(id2label[i], predicted_class[0][i].item())
|