Upload 3 files

.gitattributes

@@ -1,39 +1 @@
-*.7z filter=lfs diff=lfs merge=lfs -text
-*.arrow filter=lfs diff=lfs merge=lfs -text
-*.bin filter=lfs diff=lfs merge=lfs -text
-*.bz2 filter=lfs diff=lfs merge=lfs -text
-*.ckpt filter=lfs diff=lfs merge=lfs -text
-*.ftz filter=lfs diff=lfs merge=lfs -text
-*.gz filter=lfs diff=lfs merge=lfs -text
-*.h5 filter=lfs diff=lfs merge=lfs -text
-*.joblib filter=lfs diff=lfs merge=lfs -text
-*.lfs.* filter=lfs diff=lfs merge=lfs -text
-*.mlmodel filter=lfs diff=lfs merge=lfs -text
-*.model filter=lfs diff=lfs merge=lfs -text
-*.msgpack filter=lfs diff=lfs merge=lfs -text
-*.npy filter=lfs diff=lfs merge=lfs -text
-*.npz filter=lfs diff=lfs merge=lfs -text
-*.onnx filter=lfs diff=lfs merge=lfs -text
-*.ot filter=lfs diff=lfs merge=lfs -text
-*.parquet filter=lfs diff=lfs merge=lfs -text
-*.pb filter=lfs diff=lfs merge=lfs -text
-*.pickle filter=lfs diff=lfs merge=lfs -text
-*.pkl filter=lfs diff=lfs merge=lfs -text
-*.pt filter=lfs diff=lfs merge=lfs -text
-*.pth filter=lfs diff=lfs merge=lfs -text
-*.rar filter=lfs diff=lfs merge=lfs -text
-*.safetensors filter=lfs diff=lfs merge=lfs -text
-saved_model/**/* filter=lfs diff=lfs merge=lfs -text
-*.tar.* filter=lfs diff=lfs merge=lfs -text
-*.tflite filter=lfs diff=lfs merge=lfs -text
-*.tgz filter=lfs diff=lfs merge=lfs -text
-*.wasm filter=lfs diff=lfs merge=lfs -text
-*.xz filter=lfs diff=lfs merge=lfs -text
-*.zip filter=lfs diff=lfs merge=lfs -text
-*.zst filter=lfs diff=lfs merge=lfs -text
-*tfevents* filter=lfs diff=lfs merge=lfs -text
-multilingual_toxic_comment_files/env/Lib/site-packages/clang/native/libclang.dll filter=lfs diff=lfs merge=lfs -text
-multilingual_toxic_comment_files/env/Lib/site-packages/cryptography/hazmat/bindings/_rust.pyd filter=lfs diff=lfs merge=lfs -text
-multilingual_toxic_comment_files/env/Lib/site-packages/grpc/_cython/cygrpc.cp310-win_amd64.pyd filter=lfs diff=lfs merge=lfs -text
-multilingual_toxic_comment_files/env/Lib/site-packages/h5py/hdf5.dll filter=lfs diff=lfs merge=lfs -text
-multilingual_toxic_comment_files/Multilingual_toxic_comment_classifier/variables/variables.data-00000-of-00001 filter=lfs diff=lfs merge=lfs -text
+Multilingual_toxic_comment_classifier/ filter=lfs diff=lfs merge=lfs -text

app.py

@@ -0,0 +1,55 @@
+import tensorflow as tf
+import gradio as gr
+import pandas as pd
+from transformers import AutoTokenizer
+
+model_save_path = "Multilingual_toxic_comment_classifier/"
+### Loading the fine-tuned model ###
+loaded_model = tf.keras.models.load_model(model_save_path)
+### Initializing the tokenizer ###
+tokenizer_ = AutoTokenizer.from_pretrained("xlm-roberta-large")
+
+examples_list = [
+    [example]
+    for example in pd.read_csv("examples/sample_comments.csv")["comment_text"].tolist()
+]
+
+
+def prep_data(text, tokenizer, max_len=192):
+    tokens = tokenizer(
+        text,
+        max_length=max_len,
+        truncation=True,
+        padding="max_length",
+        add_special_tokens=True,
+        return_tensors="tf",
+    )
+
+    return {
+        "input_ids": tokens["input_ids"],
+        "attention_mask": tokens["attention_mask"],
+    }
+
+
+def predict(text):
+    prob_of_toxic_comment = loaded_model.predict(
+        prep_data(text=text, tokenizer=tokenizer_, max_len=192)
+    )[0][0]
+    prob_of_non_toxic_comment = 1 - prob_of_toxic_comment
+    prob_of_toxic_comment, prob_of_non_toxic_comment
+    probs = {
+        "prob_of_toxic_comment": float(prob_of_toxic_comment),
+        "prob_of_non_toxic_comment": float(prob_of_non_toxic_comment),
+    }
+    return probs
+
+
+interface = gr.Interface(
+    fn=predict,
+    inputs=gr.components.Textbox(lines=4, label="Comment"),
+    outputs=[gr.Label(label="Probabilities")],
+    examples=examples_list,
+    title="Multi-Lingual Toxic Comment Classification.",
+    description="XLM-Roberta Large model",
+)
+interface.launch(debug=False, share=True)

requirements.txt

@@ -0,0 +1,4 @@
+tensorflow==2.12
+pandas==1.5.2
+gradio==3.1.4
+transformers==4.28.1