Upload 4 files

app.py

@@ -0,0 +1,28 @@
+import tensorflow as tf
+import gradio as gr
+import pandas as pd
+import pickle
+from keras.utils import pad_sequences
+
+max_len = 200
+
+# set the vocabulary mapping on a new TextVectorization layer
+with open('tokenizer.pickle', 'rb') as handle:
+    tokenizer = pickle.load(handle)
+model = tf.keras.models.load_model('toxic.h5')
+
+
+arr=["toxic","severe_toxic","obscene threat","insult","identity_hate"]
+def score_comment(comment):
+    sequences = tokenizer.texts_to_sequences([comment])
+    input = pad_sequences(sequences,maxlen=max_len)
+    results = model.predict(input)
+    text = ''
+    for i in range(len(arr)):
+        text += '{}: {}\n'.format(arr[i], results[0][i]>0.5)
+    return text
+
+interface = gr.Interface(fn=score_comment, 
+                         inputs=gr.inputs.Textbox(lines=2, placeholder='Comment to score'),
+                        outputs='text')
+interface.launch(share=True)

requirements.txt

@@ -0,0 +1,5 @@
+gradio==3.36.1
+keras==2.13.1
+pandas==2.0.3
+Pillow==10.0.0
+tensorflow==2.13.0

tokenizer.pickle

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d77d70fdcb351caea5ee6d9dfbd607f61ac419b4a04ec521d84605bbc9f41165
+size 7740158

toxic.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:73b4cc477172e73a10c43cc26bc3c628a71b2a2a6c145b5edf6a8ce42d4905e8
+size 1816640